{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BXPERG4BDDTXRWVMQR32UDG6PP","short_pith_number":"pith:BXPERG4B","schema_version":"1.0","canonical_sha256":"0dde489b8118e778daac8477aa0cde7bf4d6c5e9ebc3aff00b51530aa4003a34","source":{"kind":"arxiv","id":"2509.04491","version":1},"attestation_state":"computed","paper":{"title":"Refining Transcripts With TV Subtitles by Prompt-Based Weakly Supervised Training of ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Xinnian Zhao","submitted_at":"2025-09-01T11:43:07Z","abstract_excerpt":"This study proposes a novel approach to using TV subtitles within a weakly supervised (WS) Automatic Speech Recognition (ASR) framework. Although TV subtitles are readily available, their imprecise alignment with corresponding audio limits their applicability as supervised targets for verbatim transcription. Rather than using subtitles as direct supervision signals, our method reimagines them as context-rich prompts. This design enables the model to handle discrepancies between spoken audio and subtitle text. Instead, generated pseudo transcripts become the primary targets, with subtitles acti"},"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":"2509.04491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T11:43:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a21d9afe1cc4001e2efe7df51d4e0ea639a07bad81ec4a287835281a6e40df4d","abstract_canon_sha256":"0e1c3942097519fb330e9ca19504d098dd2ef75b2c76f332b368a7af448285d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:23.977397Z","signature_b64":"xPlFqBDlGpl36xkmTeTQbRyMlMPpvuJFkPFcywQEu8LvBbQ++kFNugFS+98XuREMHkpcEkYNOZiXWU0mxX5+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dde489b8118e778daac8477aa0cde7bf4d6c5e9ebc3aff00b51530aa4003a34","last_reissued_at":"2026-07-05T12:05:23.976918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:23.976918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refining Transcripts With TV Subtitles by Prompt-Based Weakly Supervised Training of ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Xinnian Zhao","submitted_at":"2025-09-01T11:43:07Z","abstract_excerpt":"This study proposes a novel approach to using TV subtitles within a weakly supervised (WS) Automatic Speech Recognition (ASR) framework. Although TV subtitles are readily available, their imprecise alignment with corresponding audio limits their applicability as supervised targets for verbatim transcription. Rather than using subtitles as direct supervision signals, our method reimagines them as context-rich prompts. This design enables the model to handle discrepancies between spoken audio and subtitle text. Instead, generated pseudo transcripts become the primary targets, with subtitles acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04491","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/2509.04491/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":"2509.04491","created_at":"2026-07-05T12:05:23.976973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04491v1","created_at":"2026-07-05T12:05:23.976973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04491","created_at":"2026-07-05T12:05:23.976973+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXPERG4BDDTX","created_at":"2026-07-05T12:05:23.976973+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXPERG4BDDTXRWVM","created_at":"2026-07-05T12:05:23.976973+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXPERG4B","created_at":"2026-07-05T12:05:23.976973+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/BXPERG4BDDTXRWVMQR32UDG6PP","json":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP.json","graph_json":"https://pith.science/api/pith-number/BXPERG4BDDTXRWVMQR32UDG6PP/graph.json","events_json":"https://pith.science/api/pith-number/BXPERG4BDDTXRWVMQR32UDG6PP/events.json","paper":"https://pith.science/paper/BXPERG4B"},"agent_actions":{"view_html":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP","download_json":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP.json","view_paper":"https://pith.science/paper/BXPERG4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04491&json=true","fetch_graph":"https://pith.science/api/pith-number/BXPERG4BDDTXRWVMQR32UDG6PP/graph.json","fetch_events":"https://pith.science/api/pith-number/BXPERG4BDDTXRWVMQR32UDG6PP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP/action/storage_attestation","attest_author":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP/action/author_attestation","sign_citation":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP/action/citation_signature","submit_replication":"https://pith.science/pith/BXPERG4BDDTXRWVMQR32UDG6PP/action/replication_record"}},"created_at":"2026-07-05T12:05:23.976973+00:00","updated_at":"2026-07-05T12:05:23.976973+00:00"}