diff --git a/teaching/proposals/proposals.jsonl b/teaching/proposals/proposals.jsonl index 4ed5e313..1e6c6964 100644 --- a/teaching/proposals/proposals.jsonl +++ b/teaching/proposals/proposals.jsonl @@ -48,3 +48,9 @@ {"event":"replay","proposal_id":"46ce297f797ff16da12db5de422ca3c9","replay_evidence":{"baseline":{"intent_accuracy":1.0,"surface_groundedness":1.0,"term_capture_rate":1.0,"versor_closure_rate":1.0},"candidate":{"intent_accuracy":1.0,"surface_groundedness":1.0,"term_capture_rate":1.0,"versor_closure_rate":1.0},"capability_axes":{"G1_verb_classes":{"correct":20,"refused":0,"wrong":0},"G2_comparatives":{"correct":29,"refused":0,"wrong":0},"G3_numerics":{"correct":20,"refused":6,"wrong":0},"G4_multi_clause":{"correct":32,"refused":0,"wrong":0},"G5_aggregate":{"correct":20,"refused":0,"wrong":0},"S1_rate_events":{"correct":20,"refused":0,"wrong":0}},"gsm8k_train_sample":{"correct":3,"refused":47,"wrong":0},"regressed_metrics":[],"replay_equivalent":true,"wrong_count_delta":0}} {"event":"created","proposal":{"claim_domain":"factual","evidence":[{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:gsm8k-train-sample-v1-0013","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:gsm8k-train-sample-v1-0014","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:gsm8k-train-sample-v1-0024","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:gsm8k-train-sample-v1-0050","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0005","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0006","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0007","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0008","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0009","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0010","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0011","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0012","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0013","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0014","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0015","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0016","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0017","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0018","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0019","source":"corpus"},{"epistemic_status":"coherent","polarity":"affirms","ref":"exemplar:ta-v1-0020","source":"corpus"}],"operator_note":"","polarity":"affirms","proposal_id":"a3b892546977c5f0f64c578d6052adbd","proposed_chain":{"connective":"recognizes","intent":"admissibility","object":"d6e31f6bc8e77067ef6388ff95b7fa47b20c51bc0ab5223c454e533909dcbb17","recognizer_spec":{"canonical_pattern":{"anchor_count_max":4,"anchor_count_min":1,"anchor_kind":"event_count_per_window","graph_intent":"aggregate","observed_window_quantifiers":["each","every","per"],"observed_window_units":["day","hour","minute","month","week"],"outcome":"admissible","shape_category":"temporal_aggregation","unresolved_notes":["'a gig' implies count=1; 'every other day' is approximated as window_quantifier='every' with unit 'day'; the outer 'for 2 weeks' duration bound is not captured by the current schema.","'daily' is treated as window_unit='day' with quantifier='per'; the adverbial form has no explicit quantifier word.","'every other day' approximated as window_quantifier='every'; the 'other' (skip-one) cadence is not represented in the schema.","Day-of-week enumeration is encoded as four day-windowed event_count anchors; specific day-of-week labels (Mon/Tue/Wed/Thu) are not captured because the schema lacks a day-of-week field.","Edge case: 'in N minutes' window framing (no 'each/every/per' word). Mirrors train case 0014 but with a different count/unit pairing; window_quantifier is mapped to 'per' and the '30' multiplier is implicit.","Edge case: 'over N hours' temporal-window framing. As with case 0014, the schema collapses '80 per 6 hours' to window_unit='hour' with quantifier='per'.","Edge case: minimal day-of-week enumeration (exactly two distinct day names \u2014 the threshold for the rule). Distinct from case 0024 which enumerates four days.","The 'one-hour' detail describes video length, not the aggregation window; it is intentionally omitted from quantity_anchors so Phase C generalizes the window-axis cleanly.","The window is 5 minutes (composite count + unit); the schema only encodes window_unit/quantifier, so 'per' is the closest canonical quantifier and the '5' multiplier is implicit. Phase C may need a window_count extension to express '10 per 5 minutes' versus '10 per minute' precisely.","count_token here refers to the per-day quantity (2 hours of practice); the inner unit 'hours' is part of the counted thing, not the window.","count_token=90 refers to minutes-of-practice per day; the inner unit 'minutes' is part of the counted thing."]},"coverage":{"anchors_event_count_per_window":24,"window_quantifier:each":11,"window_quantifier:every":5,"window_quantifier:per":8,"window_unit:day":15,"window_unit:hour":2,"window_unit:minute":2,"window_unit:month":1,"window_unit:week":4},"exemplar_count":20,"exemplar_digest":"cca6491bac0df6e9c935d38cefc8d421de9ea6761b34e2f8bf99f9e543c95e82","shape_category":"temporal_aggregation"},"subject":"temporal_aggregation"},"provenance":null,"replay_evidence":null,"review_state":"pending","source":{"emitted_at_revision":"08c5e0e82feba5835b6b5e8a40dee1c590b10263","kind":"exemplar_corpus","source_id":"cca6491bac0df6e9c935d38cefc8d421de9ea6761b34e2f8bf99f9e543c95e82"},"source_candidate_id":"71c76cbfd6ee52075ba78fa31b7a23490762d9bac7779c00ce293a362e23d2b2"}} {"event":"replay","proposal_id":"a3b892546977c5f0f64c578d6052adbd","replay_evidence":{"baseline":{"intent_accuracy":1.0,"surface_groundedness":1.0,"term_capture_rate":1.0,"versor_closure_rate":1.0},"candidate":{"intent_accuracy":1.0,"surface_groundedness":1.0,"term_capture_rate":1.0,"versor_closure_rate":1.0},"capability_axes":{"G1_verb_classes":{"correct":20,"refused":0,"wrong":0},"G2_comparatives":{"correct":29,"refused":0,"wrong":0},"G3_numerics":{"correct":20,"refused":6,"wrong":0},"G4_multi_clause":{"correct":32,"refused":0,"wrong":0},"G5_aggregate":{"correct":20,"refused":0,"wrong":0},"S1_rate_events":{"correct":20,"refused":0,"wrong":0}},"gsm8k_train_sample":{"correct":3,"refused":47,"wrong":0},"regressed_metrics":[],"replay_equivalent":true,"wrong_count_delta":0}} +{"event":"transition","note":"","proposal_id":"59223f13722f906a1cf9b65d9b01c990","to":"accepted"} +{"chain_id":"admissibility_descriptive_setup_no_quantity_recognizes_47ae70324a9a8d7057c7efacfaf180a4afd07e371896af92f9d24d0a1ef04651","event":"accepted_corpus_append","proposal_id":"59223f13722f906a1cf9b65d9b01c990","provenance":{"adr_id":"adr-0057","raw":"adr-0057:discovery_promoted:2026-05-27","review_date":"2026-05-27","source":"discovery_promoted"}} +{"event":"transition","note":"","proposal_id":"46ce297f797ff16da12db5de422ca3c9","to":"accepted"} +{"chain_id":"admissibility_rate_with_currency_recognizes_7741c837933c975e52d01fe4a97d18c6609cce3dceaf934ba6eccefda0c6837a","event":"accepted_corpus_append","proposal_id":"46ce297f797ff16da12db5de422ca3c9","provenance":{"adr_id":"adr-0057","raw":"adr-0057:discovery_promoted:2026-05-27","review_date":"2026-05-27","source":"discovery_promoted"}} +{"event":"transition","note":"","proposal_id":"a3b892546977c5f0f64c578d6052adbd","to":"accepted"} +{"chain_id":"admissibility_temporal_aggregation_recognizes_d6e31f6bc8e77067ef6388ff95b7fa47b20c51bc0ab5223c454e533909dcbb17","event":"accepted_corpus_append","proposal_id":"a3b892546977c5f0f64c578d6052adbd","provenance":{"adr_id":"adr-0057","raw":"adr-0057:discovery_promoted:2026-05-27","review_date":"2026-05-27","source":"discovery_promoted"}}