{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LYI47JO4FUYUYEXE44HBKRYYLV","short_pith_number":"pith:LYI47JO4","canonical_record":{"source":{"id":"2501.05234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T13:41:37Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"8fe0d576f2610855fa9f932a96b50669c4aa7eb08cfc21c0f4f42031dc7216b4","abstract_canon_sha256":"939688a10f7765f6a69279ab0eded1f82f1732a14937cfc1bb68db013aab3e76"},"schema_version":"1.0"},"canonical_sha256":"5e11cfa5dc2d314c12e4e70e1547185d66d0b6a743171eae8e7d32dcdc329254","source":{"kind":"arxiv","id":"2501.05234","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LYI47JO4FUYUYEXE44HBKRYYLV","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T13:41:37Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"8fe0d576f2610855fa9f932a96b50669c4aa7eb08cfc21c0f4f42031dc7216b4","abstract_canon_sha256":"939688a10f7765f6a69279ab0eded1f82f1732a14937cfc1bb68db013aab3e76"},"schema_version":"1.0"},"canonical_sha256":"5e11cfa5dc2d314c12e4e70e1547185d66d0b6a743171eae8e7d32dcdc329254","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:06.892780Z","signature_b64":"P12SOkRoPJErftMHb7xzQ0iQklB56BoA+7QddQL9/gElnBPWOTaYtqZrdLa6bvlyNfo90QJtIwdufa4a2aw7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e11cfa5dc2d314c12e4e70e1547185d66d0b6a743171eae8e7d32dcdc329254","last_reissued_at":"2026-07-05T09:59:06.892329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:06.892329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05234","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":"2026-07-05T09:59:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Du3bNdlzOWc2HENYytn4A5BcHciaTEPWlq4cAfG4HlrqpRGwwEu1J+2cokaHIvj07PaVIqPH3OU48BduvSO3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:20:04.397056Z"},"content_sha256":"71f5dfc32dc6963d99d133efb0caee954d8641115d5b42503deb236454819527","schema_version":"1.0","event_id":"sha256:71f5dfc32dc6963d99d133efb0caee954d8641115d5b42503deb236454819527"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LYI47JO4FUYUYEXE44HBKRYYLV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Artem Fedorchenko, Tanel Alum\\\"ae","submitted_at":"2025-01-09T13:41:37Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05234","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/2501.05234/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":"2026-07-05T09:59:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8aMrdlMZlkFzbnWBiojkNo3WVuT1MBJZTabiP13wgBTKLQhHzxGiatzLrNH/K0jp52/RyIThHLrTF9S8DA5wBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:20:04.397502Z"},"content_sha256":"0bce4e86ca79e3ecd88c5c45ba686a9d1bd8b748d889b50b2f67f63dc342ee6e","schema_version":"1.0","event_id":"sha256:0bce4e86ca79e3ecd88c5c45ba686a9d1bd8b748d889b50b2f67f63dc342ee6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYI47JO4FUYUYEXE44HBKRYYLV/bundle.json","state_url":"https://pith.science/pith/LYI47JO4FUYUYEXE44HBKRYYLV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYI47JO4FUYUYEXE44HBKRYYLV/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":"2026-08-13T15:20:04Z","links":{"resolver":"https://pith.science/pith/LYI47JO4FUYUYEXE44HBKRYYLV","bundle":"https://pith.science/pith/LYI47JO4FUYUYEXE44HBKRYYLV/bundle.json","state":"https://pith.science/pith/LYI47JO4FUYUYEXE44HBKRYYLV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYI47JO4FUYUYEXE44HBKRYYLV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ION3cQb+X0wPZnYuV+rgQBQvpDeIsPOkk6rGrFaEc+rvdIKIIcMd1rRPxKfn7FWHyonx4oD69CVO2YcxXlx7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:20:04.400607Z","bundle_sha256":"4cac57ce824e535ed6d8c8ca4a087a388db4c2f6552cda16940ddc9d5232ce39"}}