{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JD75TWRR57MMDJWCFIDTC7TPF7","short_pith_number":"pith:JD75TWRR","canonical_record":{"source":{"id":"2505.21578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T08:40:28Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b47eb376c00e9744df1b2ba1f93e8771b514ec3af5690f9abef6987e9cdb208d","abstract_canon_sha256":"58db5979f4e7639e41a0b4c3f167003f691bd45de13da3d0837d6a5fd4aa3e02"},"schema_version":"1.0"},"canonical_sha256":"48ffd9da31efd8c1a6c22a07317e6f2febcc5ddd2f9ed740664cff28ec989cf3","source":{"kind":"arxiv","id":"2505.21578","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21578","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21578v1","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21578","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"JD75TWRR57MM","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_16","alias_value":"JD75TWRR57MMDJWC","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_8","alias_value":"JD75TWRR","created_at":"2026-07-05T11:11:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JD75TWRR57MMDJWCFIDTC7TPF7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T08:40:28Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b47eb376c00e9744df1b2ba1f93e8771b514ec3af5690f9abef6987e9cdb208d","abstract_canon_sha256":"58db5979f4e7639e41a0b4c3f167003f691bd45de13da3d0837d6a5fd4aa3e02"},"schema_version":"1.0"},"canonical_sha256":"48ffd9da31efd8c1a6c22a07317e6f2febcc5ddd2f9ed740664cff28ec989cf3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:00.353141Z","signature_b64":"OXbQE6drMLKchZJFw+w/GI0DOMVNalzO1wv04vqTy94FRIbq//+Nl+DRmY5KivngGad/PesybhCgvECMLhT0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48ffd9da31efd8c1a6c22a07317e6f2febcc5ddd2f9ed740664cff28ec989cf3","last_reissued_at":"2026-07-05T11:11:00.352651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:00.352651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21578","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":"2026-07-05T11:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5slfjAP8Tf7fsRmcDRFip/XgCKXxURa7EsdjMi68quH5U37YLFK9xI5oUEdZgFkdfX17m7kVTRXhEtQ+DVYrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:09:46.198336Z"},"content_sha256":"523a5b56e51bf29040209ed4c36d7eda41b3bf6a1cf3fe616b93b71e15d7c2f2","schema_version":"1.0","event_id":"sha256:523a5b56e51bf29040209ed4c36d7eda41b3bf6a1cf3fe616b93b71e15d7c2f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JD75TWRR57MMDJWCFIDTC7TPF7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Rogier Van Dalen, Shucong Zhang, Titouan Parcollet, Yuan Tseng","submitted_at":"2025-05-27T08:40:28Z","abstract_excerpt":"Automatic speech recognition (ASR) research is driven by the availability of common datasets between industrial researchers and academics, encouraging comparisons and evaluations. LibriSpeech, despite its long success as an ASR benchmark, is now limited by its size and focus on clean, read speech, leading to near-zero word error rates. More recent datasets, including MOSEL, YODAS, Gigaspeech, OWSM, Libriheavy or People's Speech suffer from major limitations including licenses that researchers in the industry cannot use, unreliable transcriptions, incorrect audio data, or the lack of evaluation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21578","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/2505.21578/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":"2026-07-05T11:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kA17d63dkNzSVHmMZBlQ89o28kdEoTrEty3bxq53sOyOVKnxWHSYtO75lPoYgfK7E22z0fkIa+47u8TqAZRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:09:46.198832Z"},"content_sha256":"aa6de379147c6a2fef67feae8e46e15131e128886019452ae3b16c915b9bbbc8","schema_version":"1.0","event_id":"sha256:aa6de379147c6a2fef67feae8e46e15131e128886019452ae3b16c915b9bbbc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JD75TWRR57MMDJWCFIDTC7TPF7/bundle.json","state_url":"https://pith.science/pith/JD75TWRR57MMDJWCFIDTC7TPF7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JD75TWRR57MMDJWCFIDTC7TPF7/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":"2026-08-08T05:09:46Z","links":{"resolver":"https://pith.science/pith/JD75TWRR57MMDJWCFIDTC7TPF7","bundle":"https://pith.science/pith/JD75TWRR57MMDJWCFIDTC7TPF7/bundle.json","state":"https://pith.science/pith/JD75TWRR57MMDJWCFIDTC7TPF7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JD75TWRR57MMDJWCFIDTC7TPF7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JD75TWRR57MMDJWCFIDTC7TPF7","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":"58db5979f4e7639e41a0b4c3f167003f691bd45de13da3d0837d6a5fd4aa3e02","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T08:40:28Z","title_canon_sha256":"b47eb376c00e9744df1b2ba1f93e8771b514ec3af5690f9abef6987e9cdb208d"},"schema_version":"1.0","source":{"id":"2505.21578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21578","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21578v1","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21578","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"JD75TWRR57MM","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_16","alias_value":"JD75TWRR57MMDJWC","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_8","alias_value":"JD75TWRR","created_at":"2026-07-05T11:11:00Z"}],"graph_snapshots":[{"event_id":"sha256:aa6de379147c6a2fef67feae8e46e15131e128886019452ae3b16c915b9bbbc8","target":"graph","created_at":"2026-07-05T11:11:00Z","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/2505.21578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic speech recognition (ASR) research is driven by the availability of common datasets between industrial researchers and academics, encouraging comparisons and evaluations. LibriSpeech, despite its long success as an ASR benchmark, is now limited by its size and focus on clean, read speech, leading to near-zero word error rates. More recent datasets, including MOSEL, YODAS, Gigaspeech, OWSM, Libriheavy or People's Speech suffer from major limitations including licenses that researchers in the industry cannot use, unreliable transcriptions, incorrect audio data, or the lack of evaluation","authors_text":"Rogier Van Dalen, Shucong Zhang, Titouan Parcollet, Yuan Tseng","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T08:40:28Z","title":"Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21578","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":"sha256:523a5b56e51bf29040209ed4c36d7eda41b3bf6a1cf3fe616b93b71e15d7c2f2","target":"record","created_at":"2026-07-05T11:11:00Z","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":"58db5979f4e7639e41a0b4c3f167003f691bd45de13da3d0837d6a5fd4aa3e02","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T08:40:28Z","title_canon_sha256":"b47eb376c00e9744df1b2ba1f93e8771b514ec3af5690f9abef6987e9cdb208d"},"schema_version":"1.0","source":{"id":"2505.21578","kind":"arxiv","version":1}},"canonical_sha256":"48ffd9da31efd8c1a6c22a07317e6f2febcc5ddd2f9ed740664cff28ec989cf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48ffd9da31efd8c1a6c22a07317e6f2febcc5ddd2f9ed740664cff28ec989cf3","first_computed_at":"2026-07-05T11:11:00.352651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:00.352651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OXbQE6drMLKchZJFw+w/GI0DOMVNalzO1wv04vqTy94FRIbq//+Nl+DRmY5KivngGad/PesybhCgvECMLhT0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:00.353141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:523a5b56e51bf29040209ed4c36d7eda41b3bf6a1cf3fe616b93b71e15d7c2f2","sha256:aa6de379147c6a2fef67feae8e46e15131e128886019452ae3b16c915b9bbbc8"],"state_sha256":"8a172afe68e23192c855d5eefaf761532d03863b048f48ce9ba5334c6657fcd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHXj6/PtaRVVglXZpqRCbcCQSFIZybcaHbpZh1XD1d8KPB9dH2vgXAoLtEXAlxsdPJZ5EqMqQfSbbu8zvbArAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:09:46.202067Z","bundle_sha256":"fba97c85ce39a6419b983ac2ae786e860ce21eb47c5f1d7e34edfd80525dbac6"}}