{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y4BLRL74USIVIR7L362OHVOEXX","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":"92af256f99be5a43cdc5eba7961a32c10c56871fdfa95e89b3162473a2b92c62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T14:52:42Z","title_canon_sha256":"b76b2968b16f3d06bdc11b5347d6416702bdef96eddfc979e907e8cd03b16b11"},"schema_version":"1.0","source":{"id":"2408.16589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16589","created_at":"2026-07-05T09:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16589v1","created_at":"2026-07-05T09:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16589","created_at":"2026-07-05T09:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"Y4BLRL74USIV","created_at":"2026-07-05T09:00:43Z"},{"alias_kind":"pith_short_16","alias_value":"Y4BLRL74USIVIR7L","created_at":"2026-07-05T09:00:43Z"},{"alias_kind":"pith_short_8","alias_value":"Y4BLRL74","created_at":"2026-07-05T09:00:43Z"}],"graph_snapshots":[{"event_id":"sha256:a9ba86cc6cbae8bf621025be8aa67d8787794ee8deb9dbd0e618c50868cbd7de","target":"graph","created_at":"2026-07-05T09:00:43Z","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/2408.16589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic time warping to the decoder's cross-attention scores. We fine-tune the model to produce more verbatim speech transcriptions and employ several techniques to increase robustness against multiple speakers and background noise. These adjustments achieve state-of-the-art performance on benchmarks for verbatim speech transcription, word segmentation, and the timed detection of filler events, and can further mitigate transcr","authors_text":"Bernhard Thallinger, Laurin Wagner, Mario Zusag","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T14:52:42Z","title":"CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16589","kind":"arxiv","version":1},"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":"sha256:508bb8f87c9995565ebe04213a0de80a8b84988cc6badd21d4ff8b40a1ac4acf","target":"record","created_at":"2026-07-05T09:00:43Z","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":"92af256f99be5a43cdc5eba7961a32c10c56871fdfa95e89b3162473a2b92c62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T14:52:42Z","title_canon_sha256":"b76b2968b16f3d06bdc11b5347d6416702bdef96eddfc979e907e8cd03b16b11"},"schema_version":"1.0","source":{"id":"2408.16589","kind":"arxiv","version":1}},"canonical_sha256":"c702b8affca4915447ebdfb4e3d5c4bdd6c1e9f9f724091de7df24df7694475b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c702b8affca4915447ebdfb4e3d5c4bdd6c1e9f9f724091de7df24df7694475b","first_computed_at":"2026-07-05T09:00:43.475093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:43.475093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3j40Ephr1bVLmkc9kbSH5+gIu6sUBe1X1uJxpj0InRh+F6vfLUfnPlNiJRlpVxcHMQaeKzRT/6ynYd1+TrFYAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:43.475483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:508bb8f87c9995565ebe04213a0de80a8b84988cc6badd21d4ff8b40a1ac4acf","sha256:a9ba86cc6cbae8bf621025be8aa67d8787794ee8deb9dbd0e618c50868cbd7de"],"state_sha256":"7f7a799a20468f3344fb3e26df60dd38b8053e7dd2b1423331d12bc4e8ffada3"}