{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YNPYQPVZYLUSNY4RYWZMVV5L7H","short_pith_number":"pith:YNPYQPVZ","schema_version":"1.0","canonical_sha256":"c35f883eb9c2e926e391c5b2cad7abf9d13b7df11883bee1a05126889fcd647c","source":{"kind":"arxiv","id":"2606.23306","version":1},"attestation_state":"computed","paper":{"title":"The Anatomy of the CTC Oracle Gap: Acoustic Exhaustion and Linguistic Recovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ivan Novosad","submitted_at":"2026-06-22T13:21:09Z","abstract_excerpt":"We study the limits of CTC-internal scoring for N-best hypothesis selection and locate the information bottleneck separating acoustic confidence from linguistic plausibility. Eleven CTC-internal and acoustic-feature scoring strategies produce no statistically significant WER improvement over greedy decoding on LibriSpeech dev-other at G=16 (all p > 0.05). The exhaustion is systematic: CTC's Spearman $\\rho$ between hypothesis score and per-utterance WER degrades from -0.574 at G=4 to -0.270 at G=128, a 53% loss driven by blank-path proliferation. This establishes that the discriminative capacit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.23306","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T13:21:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b86b0c4e30b0aedb071f483f622db5fa818bc0c3370cd1ccd37b0183187bb327","abstract_canon_sha256":"90bf5ef0505459ef529d887f22b814efc2789bbbc390f12309ea79405bbe4c10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:16.433810Z","signature_b64":"jJj1JW9C+rUzSSW4ttWUwYE1UMOPNzK/cfnE7J4OALdBRrNHT68A9yExu5/P+7v+U7NKIK258kT6dZbx92FTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c35f883eb9c2e926e391c5b2cad7abf9d13b7df11883bee1a05126889fcd647c","last_reissued_at":"2026-06-23T03:14:16.433461Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:16.433461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Anatomy of the CTC Oracle Gap: Acoustic Exhaustion and Linguistic Recovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ivan Novosad","submitted_at":"2026-06-22T13:21:09Z","abstract_excerpt":"We study the limits of CTC-internal scoring for N-best hypothesis selection and locate the information bottleneck separating acoustic confidence from linguistic plausibility. Eleven CTC-internal and acoustic-feature scoring strategies produce no statistically significant WER improvement over greedy decoding on LibriSpeech dev-other at G=16 (all p > 0.05). The exhaustion is systematic: CTC's Spearman $\\rho$ between hypothesis score and per-utterance WER degrades from -0.574 at G=4 to -0.270 at G=128, a 53% loss driven by blank-path proliferation. This establishes that the discriminative capacit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23306","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.23306/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.23306","created_at":"2026-06-23T03:14:16.433518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23306v1","created_at":"2026-06-23T03:14:16.433518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23306","created_at":"2026-06-23T03:14:16.433518+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNPYQPVZYLUS","created_at":"2026-06-23T03:14:16.433518+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNPYQPVZYLUSNY4R","created_at":"2026-06-23T03:14:16.433518+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNPYQPVZ","created_at":"2026-06-23T03:14:16.433518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H","json":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H.json","graph_json":"https://pith.science/api/pith-number/YNPYQPVZYLUSNY4RYWZMVV5L7H/graph.json","events_json":"https://pith.science/api/pith-number/YNPYQPVZYLUSNY4RYWZMVV5L7H/events.json","paper":"https://pith.science/paper/YNPYQPVZ"},"agent_actions":{"view_html":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H","download_json":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H.json","view_paper":"https://pith.science/paper/YNPYQPVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23306&json=true","fetch_graph":"https://pith.science/api/pith-number/YNPYQPVZYLUSNY4RYWZMVV5L7H/graph.json","fetch_events":"https://pith.science/api/pith-number/YNPYQPVZYLUSNY4RYWZMVV5L7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H/action/storage_attestation","attest_author":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H/action/author_attestation","sign_citation":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H/action/citation_signature","submit_replication":"https://pith.science/pith/YNPYQPVZYLUSNY4RYWZMVV5L7H/action/replication_record"}},"created_at":"2026-06-23T03:14:16.433518+00:00","updated_at":"2026-06-23T03:14:16.433518+00:00"}