{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y4BLRL74USIVIR7L362OHVOEXX","short_pith_number":"pith:Y4BLRL74","canonical_record":{"source":{"id":"2408.16589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T14:52:42Z","cross_cats_sorted":[],"title_canon_sha256":"b76b2968b16f3d06bdc11b5347d6416702bdef96eddfc979e907e8cd03b16b11","abstract_canon_sha256":"92af256f99be5a43cdc5eba7961a32c10c56871fdfa95e89b3162473a2b92c62"},"schema_version":"1.0"},"canonical_sha256":"c702b8affca4915447ebdfb4e3d5c4bdd6c1e9f9f724091de7df24df7694475b","source":{"kind":"arxiv","id":"2408.16589","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y4BLRL74USIVIR7L362OHVOEXX","target":"record","payload":{"canonical_record":{"source":{"id":"2408.16589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T14:52:42Z","cross_cats_sorted":[],"title_canon_sha256":"b76b2968b16f3d06bdc11b5347d6416702bdef96eddfc979e907e8cd03b16b11","abstract_canon_sha256":"92af256f99be5a43cdc5eba7961a32c10c56871fdfa95e89b3162473a2b92c62"},"schema_version":"1.0"},"canonical_sha256":"c702b8affca4915447ebdfb4e3d5c4bdd6c1e9f9f724091de7df24df7694475b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:43.475483Z","signature_b64":"3j40Ephr1bVLmkc9kbSH5+gIu6sUBe1X1uJxpj0InRh+F6vfLUfnPlNiJRlpVxcHMQaeKzRT/6ynYd1+TrFYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c702b8affca4915447ebdfb4e3d5c4bdd6c1e9f9f724091de7df24df7694475b","last_reissued_at":"2026-07-05T09:00:43.475093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:43.475093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.16589","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5bnoAavjzFCwVBFfRyBnGE6T9NdeyWITDhRsvaOeXBOrsEWc0h0uluTrkH0H95BkTtLm5DpJBBvIerHt59MAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:54:19.201338Z"},"content_sha256":"508bb8f87c9995565ebe04213a0de80a8b84988cc6badd21d4ff8b40a1ac4acf","schema_version":"1.0","event_id":"sha256:508bb8f87c9995565ebe04213a0de80a8b84988cc6badd21d4ff8b40a1ac4acf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y4BLRL74USIVIR7L362OHVOEXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernhard Thallinger, Laurin Wagner, Mario Zusag","submitted_at":"2024-08-29T14:52:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16589","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/2408.16589/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l4GfEYHFChX08/6N5kIBVj5Hr1qecqA5GwPeob23mMbq977FEmuqZ0KDZHqh0Be4ABJp6ekwrFLAD8FTUKDsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:54:19.202121Z"},"content_sha256":"a9ba86cc6cbae8bf621025be8aa67d8787794ee8deb9dbd0e618c50868cbd7de","schema_version":"1.0","event_id":"sha256:a9ba86cc6cbae8bf621025be8aa67d8787794ee8deb9dbd0e618c50868cbd7de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4BLRL74USIVIR7L362OHVOEXX/bundle.json","state_url":"https://pith.science/pith/Y4BLRL74USIVIR7L362OHVOEXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4BLRL74USIVIR7L362OHVOEXX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T05:54:19Z","links":{"resolver":"https://pith.science/pith/Y4BLRL74USIVIR7L362OHVOEXX","bundle":"https://pith.science/pith/Y4BLRL74USIVIR7L362OHVOEXX/bundle.json","state":"https://pith.science/pith/Y4BLRL74USIVIR7L362OHVOEXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4BLRL74USIVIR7L362OHVOEXX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"70JGYlAutfAJ10HQUlN00UrU+v0qdKUP86ILIC/cLqIQDz9x9RtkpgcZPgN1fEG3Tgb4tq64282zbIUkAmoGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:54:19.210993Z","bundle_sha256":"2067e4397fee3c4327056460aa82931ede310f91906d83d4bb52570345528596"}}