{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V4MJ4BNZ25WKAF3ASBM2XZTTL6","short_pith_number":"pith:V4MJ4BNZ","canonical_record":{"source":{"id":"2502.03212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-05T14:26:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"089757389ab323da556242cbc2b78fd3d839ca85885752370a22c922da2f50c7","abstract_canon_sha256":"cd5ebe5711d82f8c030a28873daacbd68dad4811291cad149a861c44b70c4d97"},"schema_version":"1.0"},"canonical_sha256":"af189e05b9d76ca017609059abe6735fb487f47c0b59ac95c3188bcdab7e30b2","source":{"kind":"arxiv","id":"2502.03212","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03212","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03212v1","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03212","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"V4MJ4BNZ25WK","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"V4MJ4BNZ25WKAF3A","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"V4MJ4BNZ","created_at":"2026-07-05T10:10:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V4MJ4BNZ25WKAF3ASBM2XZTTL6","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-05T14:26:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"089757389ab323da556242cbc2b78fd3d839ca85885752370a22c922da2f50c7","abstract_canon_sha256":"cd5ebe5711d82f8c030a28873daacbd68dad4811291cad149a861c44b70c4d97"},"schema_version":"1.0"},"canonical_sha256":"af189e05b9d76ca017609059abe6735fb487f47c0b59ac95c3188bcdab7e30b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:01.499890Z","signature_b64":"EpGiYLooJkvSggPu+SVdRB4NZ7xom8jecJjA01tAGERQ5Yfm9zBwyDLKi9N4EhCa5SreC3OeEjYpSJDLLB4eAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af189e05b9d76ca017609059abe6735fb487f47c0b59ac95c3188bcdab7e30b2","last_reissued_at":"2026-07-05T10:10:01.499479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:01.499479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03212","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":"2026-07-05T10:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Obovv2Tj+AwbuoaGinzvZR/KJn4PKdgfNw3DPS7zsOp6Tmcs5Z5UiHoRRs+fW4ZrpUS4s6Ew+gRpo1Z+91PgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T23:53:30.953951Z"},"content_sha256":"d81276820d00e293332b2081c0ce57b66b1e053109ee6fe0ccfa34eee9937338","schema_version":"1.0","event_id":"sha256:d81276820d00e293332b2081c0ce57b66b1e053109ee6fe0ccfa34eee9937338"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V4MJ4BNZ25WKAF3ASBM2XZTTL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and Subtitling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Jakob Poncelet","submitted_at":"2025-02-05T14:26:58Z","abstract_excerpt":"The recent advancement of speech recognition technology has been driven by large-scale datasets and attention-based architectures, but many challenges still remain, especially for low-resource languages and dialects. This paper explores the integration of weakly supervised transcripts from TV subtitles into automatic speech recognition (ASR) systems, aiming to improve both verbatim transcriptions and automatically generated subtitles. To this end, verbatim data and subtitles are regarded as different domains or languages, due to their distinct characteristics. We propose and compare several en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03212","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/2502.03212/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":"2026-07-05T10:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kBKJnYfZxCozzqWEI5HpRx/p7FPv/vbiRsxTojtBDcr6XWDVis6DQH8py9t1JgBSFnb4vgXioP6XQcgJ/RPJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T23:53:30.954325Z"},"content_sha256":"aebbd884ce85d1ae170bc31a39c10e6f16bfc83720e1afe45b3062528370db23","schema_version":"1.0","event_id":"sha256:aebbd884ce85d1ae170bc31a39c10e6f16bfc83720e1afe45b3062528370db23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4MJ4BNZ25WKAF3ASBM2XZTTL6/bundle.json","state_url":"https://pith.science/pith/V4MJ4BNZ25WKAF3ASBM2XZTTL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4MJ4BNZ25WKAF3ASBM2XZTTL6/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":"2026-07-16T23:53:30Z","links":{"resolver":"https://pith.science/pith/V4MJ4BNZ25WKAF3ASBM2XZTTL6","bundle":"https://pith.science/pith/V4MJ4BNZ25WKAF3ASBM2XZTTL6/bundle.json","state":"https://pith.science/pith/V4MJ4BNZ25WKAF3ASBM2XZTTL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4MJ4BNZ25WKAF3ASBM2XZTTL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V4MJ4BNZ25WKAF3ASBM2XZTTL6","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":"cd5ebe5711d82f8c030a28873daacbd68dad4811291cad149a861c44b70c4d97","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-05T14:26:58Z","title_canon_sha256":"089757389ab323da556242cbc2b78fd3d839ca85885752370a22c922da2f50c7"},"schema_version":"1.0","source":{"id":"2502.03212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03212","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03212v1","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03212","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"V4MJ4BNZ25WK","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"V4MJ4BNZ25WKAF3A","created_at":"2026-07-05T10:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"V4MJ4BNZ","created_at":"2026-07-05T10:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:aebbd884ce85d1ae170bc31a39c10e6f16bfc83720e1afe45b3062528370db23","target":"graph","created_at":"2026-07-05T10:10:01Z","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/2502.03212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advancement of speech recognition technology has been driven by large-scale datasets and attention-based architectures, but many challenges still remain, especially for low-resource languages and dialects. This paper explores the integration of weakly supervised transcripts from TV subtitles into automatic speech recognition (ASR) systems, aiming to improve both verbatim transcriptions and automatically generated subtitles. To this end, verbatim data and subtitles are regarded as different domains or languages, due to their distinct characteristics. We propose and compare several en","authors_text":"Hugo Van hamme, Jakob Poncelet","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-05T14:26:58Z","title":"Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and Subtitling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03212","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:d81276820d00e293332b2081c0ce57b66b1e053109ee6fe0ccfa34eee9937338","target":"record","created_at":"2026-07-05T10:10:01Z","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":"cd5ebe5711d82f8c030a28873daacbd68dad4811291cad149a861c44b70c4d97","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-05T14:26:58Z","title_canon_sha256":"089757389ab323da556242cbc2b78fd3d839ca85885752370a22c922da2f50c7"},"schema_version":"1.0","source":{"id":"2502.03212","kind":"arxiv","version":1}},"canonical_sha256":"af189e05b9d76ca017609059abe6735fb487f47c0b59ac95c3188bcdab7e30b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af189e05b9d76ca017609059abe6735fb487f47c0b59ac95c3188bcdab7e30b2","first_computed_at":"2026-07-05T10:10:01.499479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:01.499479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EpGiYLooJkvSggPu+SVdRB4NZ7xom8jecJjA01tAGERQ5Yfm9zBwyDLKi9N4EhCa5SreC3OeEjYpSJDLLB4eAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:01.499890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d81276820d00e293332b2081c0ce57b66b1e053109ee6fe0ccfa34eee9937338","sha256:aebbd884ce85d1ae170bc31a39c10e6f16bfc83720e1afe45b3062528370db23"],"state_sha256":"c88db0855a816808e7e6bb53433ef66f8db1bff3748d3a5b795b4fe6901ef72d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVy6g0UjnqAx6ublYRcMadFMbSDNvFMRfmV9AGLtheyOJ7PHKD3iXOHgy4lfHr33Lchy2Ymhs1P+2k1SUadSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T23:53:30.956697Z","bundle_sha256":"724b6f6604b57d3783b5e76ac8d32d8c89d1f147a5a36747e0d17cfc42bd3851"}}