{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PSBUIGWSFLAFIST36U5WVABAPC","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":"625696c9bb12849afbe5e11387aaf78cab00a02a97aa9602fc791882cb2ebf11","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:24:29Z","title_canon_sha256":"bffe1671f470531b9cf972fad52f7ab089bd967201e7cbb6d0c7493571a8343e"},"schema_version":"1.0","source":{"id":"2505.15646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15646","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15646v1","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15646","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"PSBUIGWSFLAF","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"PSBUIGWSFLAFIST3","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"PSBUIGWS","created_at":"2026-07-05T11:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:0e9e9e1fc6c98357ea77e71a8694d2000cafc89fbbcf00d7373a2c6511f5143d","target":"graph","created_at":"2026-07-05T11:06:48Z","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/2505.15646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a data-driven approach for enabling word-level timestamp prediction in the Canary model. Accurate timestamp information is crucial for a variety of downstream tasks such as speech content retrieval and timed subtitles. While traditional hybrid systems and end-to-end (E2E) models may employ external modules for timestamp prediction, our approach eliminates the need for separate alignment mechanisms. By leveraging the NeMo Forced Aligner (NFA) as a teacher model, we generate word-level timestamps and train the Canary model to predict timestamps directly. We introduce a new <|timesta","authors_text":"Boris Ginsburg, Elena Rastorgueva, Hainan Xu, He Huang, Jagadeesh Balam, Ke Hu, Krishna Puvvada, Kunal Dhawan, Shuoyang Ding, Zhehuai Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:24:29Z","title":"Word Level Timestamp Generation for Automatic Speech Recognition and Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15646","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:b8ceddb88965375a34896cd2bbb663376441e3c7f3e13f3fce5f016ebba28892","target":"record","created_at":"2026-07-05T11:06:48Z","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":"625696c9bb12849afbe5e11387aaf78cab00a02a97aa9602fc791882cb2ebf11","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:24:29Z","title_canon_sha256":"bffe1671f470531b9cf972fad52f7ab089bd967201e7cbb6d0c7493571a8343e"},"schema_version":"1.0","source":{"id":"2505.15646","kind":"arxiv","version":1}},"canonical_sha256":"7c83441ad22ac0544a7bf53b6a802078982fdabd27d1ddbeade1d670913d4445","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c83441ad22ac0544a7bf53b6a802078982fdabd27d1ddbeade1d670913d4445","first_computed_at":"2026-07-05T11:06:48.968817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:48.968817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WH2ZaECFAYIWkEy7h28wr4FqmLM3b/ETir5TaAXGbHOUje9CdFPwVqNXVgm9Ul9UPQp2brWTVlarNJi83kBCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:48.969336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8ceddb88965375a34896cd2bbb663376441e3c7f3e13f3fce5f016ebba28892","sha256:0e9e9e1fc6c98357ea77e71a8694d2000cafc89fbbcf00d7373a2c6511f5143d"],"state_sha256":"8affccf990932bbc531a87fa61ac3b1232d7d2de42d15a0fe2a32aca1769af61"}