{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IEEOFDJCIX665ZIYTWE2ZMQAUC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d717a89aca48732172a543a3d72b0645121eca44cf8b6f025bac519bb51efdaf","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-01T18:59:13Z","title_canon_sha256":"23c58f308c76257ad80d23edf27046bc7e21d88fdd276bd2a3daffad9b0c40de"},"schema_version":"1.0","source":{"id":"2303.00747","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00747","created_at":"2026-07-05T06:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00747v2","created_at":"2026-07-05T06:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00747","created_at":"2026-07-05T06:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"IEEOFDJCIX66","created_at":"2026-07-05T06:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"IEEOFDJCIX665ZIY","created_at":"2026-07-05T06:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"IEEOFDJC","created_at":"2026-07-05T06:29:41Z"}],"graph_snapshots":[{"event_id":"sha256:4d8f761d4d895609eb2a89389b11f736babb96086ae02aadf114140ad315bf30","target":"graph","created_at":"2026-07-05T06:29:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.00747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or sliding window approaches is prone to drifting, hallucination & repetition; and prohibits batched transcription due to their sequential nature. Further, timestamps corresponding each utterance are prone to inaccuracies and word-level timestamps are not available out-of-the-box. To overcome these challenges, we present WhisperX, a time-accurate speech recognition ","authors_text":"Andrew Zisserman, Jaesung Huh, Max Bain, Tengda Han","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-01T18:59:13Z","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00747","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:40ed880aaa7130e39d8c9015b15e3f8e8a3b103b411a5a8d259128e73317b3ab","target":"record","created_at":"2026-07-05T06:29:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d717a89aca48732172a543a3d72b0645121eca44cf8b6f025bac519bb51efdaf","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-01T18:59:13Z","title_canon_sha256":"23c58f308c76257ad80d23edf27046bc7e21d88fdd276bd2a3daffad9b0c40de"},"schema_version":"1.0","source":{"id":"2303.00747","kind":"arxiv","version":2}},"canonical_sha256":"4108e28d2245fdeee5189d89acb200a097357136fd05fac01ebfaa47593e90f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4108e28d2245fdeee5189d89acb200a097357136fd05fac01ebfaa47593e90f0","first_computed_at":"2026-07-05T06:29:41.861803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:41.861803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ruKJhD3EFgvKtg8rQMAS9V4nQx2CQSo4xzQIwnJ3j/9X6gbsMa2TYXacgvUfzU2AfVkX7XI53lgQ4YewtZaPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:41.862296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00747","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40ed880aaa7130e39d8c9015b15e3f8e8a3b103b411a5a8d259128e73317b3ab","sha256:4d8f761d4d895609eb2a89389b11f736babb96086ae02aadf114140ad315bf30"],"state_sha256":"aa0f92d830ab5ddef45384de5ea83f719a753ba629a505823f91f2e2e6db0385"}