{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PZU4JQC6TU6CNPC6ZUDDI546PX","short_pith_number":"pith:PZU4JQC6","schema_version":"1.0","canonical_sha256":"7e69c4c05e9d3c26bc5ecd0634779e7dfcd40c115b1c4e8134552c4be86941a8","source":{"kind":"arxiv","id":"2506.03793","version":1},"attestation_state":"computed","paper":{"title":"Mark My Words: A Robust Multilingual Model for Punctuation in Text and Speech Transcripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashwin Sankar, Raj Dabre, Sidharth Pulipaka, Sparsh Jain","submitted_at":"2025-06-04T09:54:38Z","abstract_excerpt":"Punctuation plays a vital role in structuring meaning, yet current models often struggle to restore it accurately in transcripts of spontaneous speech, especially in the presence of disfluencies such as false starts and backtracking. These limitations hinder the performance of downstream tasks like translation, text to speech, summarization, etc. where sentence boundaries are critical for preserving quality. In this work, we introduce Cadence, a generalist punctuation restoration model adapted from a pretrained large language model. Cadence is designed to handle both clean written text and hig"},"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":"2506.03793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T09:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"9e501f62e062c482ca9c237e8ab80e395df4b6d7123beadb125ccfb2af9554ef","abstract_canon_sha256":"a7b7c9a2383cbde3d2fb7d0bce1f4e5c35e859a5170b81965d9da7b09e7d0ea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:51.933140Z","signature_b64":"9kwUy5SNO5exYYxK1EHq+E4LaON5oqYB8gt7HBDxMWuBlvA/KY9/f/3JBo1lKB/eoXlAADXbT07H9ZI4fAk6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e69c4c05e9d3c26bc5ecd0634779e7dfcd40c115b1c4e8134552c4be86941a8","last_reissued_at":"2026-07-05T11:15:51.932687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:51.932687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mark My Words: A Robust Multilingual Model for Punctuation in Text and Speech Transcripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashwin Sankar, Raj Dabre, Sidharth Pulipaka, Sparsh Jain","submitted_at":"2025-06-04T09:54:38Z","abstract_excerpt":"Punctuation plays a vital role in structuring meaning, yet current models often struggle to restore it accurately in transcripts of spontaneous speech, especially in the presence of disfluencies such as false starts and backtracking. These limitations hinder the performance of downstream tasks like translation, text to speech, summarization, etc. where sentence boundaries are critical for preserving quality. In this work, we introduce Cadence, a generalist punctuation restoration model adapted from a pretrained large language model. Cadence is designed to handle both clean written text and hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03793","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/2506.03793/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":"2506.03793","created_at":"2026-07-05T11:15:51.932768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03793v1","created_at":"2026-07-05T11:15:51.932768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03793","created_at":"2026-07-05T11:15:51.932768+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZU4JQC6TU6C","created_at":"2026-07-05T11:15:51.932768+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZU4JQC6TU6CNPC6","created_at":"2026-07-05T11:15:51.932768+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZU4JQC6","created_at":"2026-07-05T11:15:51.932768+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/PZU4JQC6TU6CNPC6ZUDDI546PX","json":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX.json","graph_json":"https://pith.science/api/pith-number/PZU4JQC6TU6CNPC6ZUDDI546PX/graph.json","events_json":"https://pith.science/api/pith-number/PZU4JQC6TU6CNPC6ZUDDI546PX/events.json","paper":"https://pith.science/paper/PZU4JQC6"},"agent_actions":{"view_html":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX","download_json":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX.json","view_paper":"https://pith.science/paper/PZU4JQC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03793&json=true","fetch_graph":"https://pith.science/api/pith-number/PZU4JQC6TU6CNPC6ZUDDI546PX/graph.json","fetch_events":"https://pith.science/api/pith-number/PZU4JQC6TU6CNPC6ZUDDI546PX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX/action/storage_attestation","attest_author":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX/action/author_attestation","sign_citation":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX/action/citation_signature","submit_replication":"https://pith.science/pith/PZU4JQC6TU6CNPC6ZUDDI546PX/action/replication_record"}},"created_at":"2026-07-05T11:15:51.932768+00:00","updated_at":"2026-07-05T11:15:51.932768+00:00"}