{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LYI47JO4FUYUYEXE44HBKRYYLV","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":"939688a10f7765f6a69279ab0eded1f82f1732a14937cfc1bb68db013aab3e76","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T13:41:37Z","title_canon_sha256":"8fe0d576f2610855fa9f932a96b50669c4aa7eb08cfc21c0f4f42031dc7216b4"},"schema_version":"1.0","source":{"id":"2501.05234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05234","created_at":"2026-07-05T09:59:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05234v1","created_at":"2026-07-05T09:59:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05234","created_at":"2026-07-05T09:59:06Z"},{"alias_kind":"pith_short_12","alias_value":"LYI47JO4FUYU","created_at":"2026-07-05T09:59:06Z"},{"alias_kind":"pith_short_16","alias_value":"LYI47JO4FUYUYEXE","created_at":"2026-07-05T09:59:06Z"},{"alias_kind":"pith_short_8","alias_value":"LYI47JO4","created_at":"2026-07-05T09:59:06Z"}],"graph_snapshots":[{"event_id":"sha256:0bce4e86ca79e3ecd88c5c45ba686a9d1bd8b748d889b50b2f67f63dc342ee6e","target":"graph","created_at":"2026-07-05T09:59:06Z","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/2501.05234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an approach for generating high-quality, same-language subtitles for Estonian TV content. We fine-tune the Whisper model on human-generated Estonian subtitles and enhance it with iterative pseudo-labeling and large language model (LLM) based post-editing. Our experiments demonstrate notable subtitle quality improvement through pseudo-labeling with an unlabeled dataset. We find that applying LLM-based editing at test time enhances subtitle accuracy, while its use during training does not yield further gains. This approach holds promise for creating subtitle quality close to ","authors_text":"Artem Fedorchenko, Tanel Alum\\\"ae","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T13:41:37Z","title":"Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05234","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":"sha256:71f5dfc32dc6963d99d133efb0caee954d8641115d5b42503deb236454819527","target":"record","created_at":"2026-07-05T09:59:06Z","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":"939688a10f7765f6a69279ab0eded1f82f1732a14937cfc1bb68db013aab3e76","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T13:41:37Z","title_canon_sha256":"8fe0d576f2610855fa9f932a96b50669c4aa7eb08cfc21c0f4f42031dc7216b4"},"schema_version":"1.0","source":{"id":"2501.05234","kind":"arxiv","version":1}},"canonical_sha256":"5e11cfa5dc2d314c12e4e70e1547185d66d0b6a743171eae8e7d32dcdc329254","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e11cfa5dc2d314c12e4e70e1547185d66d0b6a743171eae8e7d32dcdc329254","first_computed_at":"2026-07-05T09:59:06.892329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:06.892329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P12SOkRoPJErftMHb7xzQ0iQklB56BoA+7QddQL9/gElnBPWOTaYtqZrdLa6bvlyNfo90QJtIwdufa4a2aw7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:06.892780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71f5dfc32dc6963d99d133efb0caee954d8641115d5b42503deb236454819527","sha256:0bce4e86ca79e3ecd88c5c45ba686a9d1bd8b748d889b50b2f67f63dc342ee6e"],"state_sha256":"45c95473e76e9886c7dc3bd1441f0689296aa8e2d672cbc60f2dff3cdaf562e7"}