{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QS3L25QIZYJQOHRINA4J32QXDA","short_pith_number":"pith:QS3L25QI","canonical_record":{"source":{"id":"2508.20869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-28T15:00:51Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"44a3157f5bbd45ce28adeb4a4401dfaaf681be6318bcf8b99e0a20efcb8428d3","abstract_canon_sha256":"eb4ba745380c71a3d575523268cbbbe625a8e2e25440fc3202e5a3277d7d1d08"},"schema_version":"1.0"},"canonical_sha256":"84b6bd7608ce13071e2868389dea1718172d3cadb70b9f9617834eaab5a6750e","source":{"kind":"arxiv","id":"2508.20869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20869","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20869v1","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20869","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"QS3L25QIZYJQ","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"QS3L25QIZYJQOHRI","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"QS3L25QI","created_at":"2026-07-05T12:01:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QS3L25QIZYJQOHRINA4J32QXDA","target":"record","payload":{"canonical_record":{"source":{"id":"2508.20869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-28T15:00:51Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"44a3157f5bbd45ce28adeb4a4401dfaaf681be6318bcf8b99e0a20efcb8428d3","abstract_canon_sha256":"eb4ba745380c71a3d575523268cbbbe625a8e2e25440fc3202e5a3277d7d1d08"},"schema_version":"1.0"},"canonical_sha256":"84b6bd7608ce13071e2868389dea1718172d3cadb70b9f9617834eaab5a6750e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:12.510096Z","signature_b64":"PfKWd4to8OwkLM274h5E3oftDh/sbKcgKalNOV9xDp1HE2scIUNwDn2HH0zX0hC+I+EareT9PM+Y0PTfS8DODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84b6bd7608ce13071e2868389dea1718172d3cadb70b9f9617834eaab5a6750e","last_reissued_at":"2026-07-05T12:01:12.509477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:12.509477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.20869","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":"2026-07-05T12:01:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zceC8N8b+IlU9i0YpZV2A6Awwb9oOR1PA1zYols3wXHqWie0lTw0kDS6fIRhgEQVgFrs4OoAnRPsZ8pX4n9HAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:50:01.761077Z"},"content_sha256":"44c026f70e3a09a67ce5fff97423fd6809ee003550e7b3062a90d754fd2d234e","schema_version":"1.0","event_id":"sha256:44c026f70e3a09a67ce5fff97423fd6809ee003550e7b3062a90d754fd2d234e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QS3L25QIZYJQOHRINA4J32QXDA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OLMoASR: Open Models and Data for Training Robust Speech Recognition Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Huong Ngo, Josh Gardner, Ludwig Schmidt, Martijn Bartelds, Matt Deitke, Matt Jordan, Sarah Pratt","submitted_at":"2025-08-28T15:00:51Z","abstract_excerpt":"Improvements in training data scale and quality have led to significant advances, yet its influence in speech recognition remains underexplored. In this paper, we present a large-scale dataset, OLMoASR-Pool, and series of models, OLMoASR, to study and develop robust zero-shot speech recognition models. Beginning from OLMoASR-Pool, a collection of 3M hours of English audio and 17M transcripts, we design text heuristic filters to remove low-quality or mistranscribed data. Our curation pipeline produces a new dataset containing 1M hours of high-quality audio-transcript pairs, which we call OLMoAS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20869","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/2508.20869/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":"2026-07-05T12:01:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WInOCerC2qaQzB5HDZPiMiDu5Yv363FZSNvYJji1VOLF+ehmtVNmEmjh3cvz06zi8ICgTK0MJnmuRMxIJh3LCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:50:01.761551Z"},"content_sha256":"b2ccaa6b69b06ca2dc3b501f761759d0483c3357bfb5051df6df714ff2c44ae5","schema_version":"1.0","event_id":"sha256:b2ccaa6b69b06ca2dc3b501f761759d0483c3357bfb5051df6df714ff2c44ae5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QS3L25QIZYJQOHRINA4J32QXDA/bundle.json","state_url":"https://pith.science/pith/QS3L25QIZYJQOHRINA4J32QXDA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QS3L25QIZYJQOHRINA4J32QXDA/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":"2026-08-22T00:50:01Z","links":{"resolver":"https://pith.science/pith/QS3L25QIZYJQOHRINA4J32QXDA","bundle":"https://pith.science/pith/QS3L25QIZYJQOHRINA4J32QXDA/bundle.json","state":"https://pith.science/pith/QS3L25QIZYJQOHRINA4J32QXDA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QS3L25QIZYJQOHRINA4J32QXDA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QS3L25QIZYJQOHRINA4J32QXDA","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":"eb4ba745380c71a3d575523268cbbbe625a8e2e25440fc3202e5a3277d7d1d08","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-28T15:00:51Z","title_canon_sha256":"44a3157f5bbd45ce28adeb4a4401dfaaf681be6318bcf8b99e0a20efcb8428d3"},"schema_version":"1.0","source":{"id":"2508.20869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20869","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20869v1","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20869","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"QS3L25QIZYJQ","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"QS3L25QIZYJQOHRI","created_at":"2026-07-05T12:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"QS3L25QI","created_at":"2026-07-05T12:01:12Z"}],"graph_snapshots":[{"event_id":"sha256:b2ccaa6b69b06ca2dc3b501f761759d0483c3357bfb5051df6df714ff2c44ae5","target":"graph","created_at":"2026-07-05T12:01:12Z","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/2508.20869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improvements in training data scale and quality have led to significant advances, yet its influence in speech recognition remains underexplored. In this paper, we present a large-scale dataset, OLMoASR-Pool, and series of models, OLMoASR, to study and develop robust zero-shot speech recognition models. Beginning from OLMoASR-Pool, a collection of 3M hours of English audio and 17M transcripts, we design text heuristic filters to remove low-quality or mistranscribed data. Our curation pipeline produces a new dataset containing 1M hours of high-quality audio-transcript pairs, which we call OLMoAS","authors_text":"Huong Ngo, Josh Gardner, Ludwig Schmidt, Martijn Bartelds, Matt Deitke, Matt Jordan, Sarah Pratt","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-28T15:00:51Z","title":"OLMoASR: Open Models and Data for Training Robust Speech Recognition Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20869","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":"sha256:44c026f70e3a09a67ce5fff97423fd6809ee003550e7b3062a90d754fd2d234e","target":"record","created_at":"2026-07-05T12:01:12Z","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":"eb4ba745380c71a3d575523268cbbbe625a8e2e25440fc3202e5a3277d7d1d08","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-28T15:00:51Z","title_canon_sha256":"44a3157f5bbd45ce28adeb4a4401dfaaf681be6318bcf8b99e0a20efcb8428d3"},"schema_version":"1.0","source":{"id":"2508.20869","kind":"arxiv","version":1}},"canonical_sha256":"84b6bd7608ce13071e2868389dea1718172d3cadb70b9f9617834eaab5a6750e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84b6bd7608ce13071e2868389dea1718172d3cadb70b9f9617834eaab5a6750e","first_computed_at":"2026-07-05T12:01:12.509477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:12.509477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PfKWd4to8OwkLM274h5E3oftDh/sbKcgKalNOV9xDp1HE2scIUNwDn2HH0zX0hC+I+EareT9PM+Y0PTfS8DODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:12.510096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44c026f70e3a09a67ce5fff97423fd6809ee003550e7b3062a90d754fd2d234e","sha256:b2ccaa6b69b06ca2dc3b501f761759d0483c3357bfb5051df6df714ff2c44ae5"],"state_sha256":"46b0600dac3029c02bb2049c4966c3e5703f97f49223867ffcb70a1c3a61d19c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QzPiCCNwOYENWfIV6pDg0y2pc4vYrq2ZduNKlIRWZeAYw/SoxMnTDGMtKcGqtWUa7Usn50HHa39FrF2IfGjYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:50:01.764332Z","bundle_sha256":"a4ac40c534831916f57fc19c771a1cc7580f8a73d0cc8bc954a31bcbb2ab553d"}}