{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IXJ6HLLEQSW7CW6XWMSC5BGSLU","short_pith_number":"pith:IXJ6HLLE","canonical_record":{"source":{"id":"2309.15013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T15:32:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c38f79cc31971b7c397309310316838d3f268db911558e41891e45d5463660de","abstract_canon_sha256":"5e4784eac8a900b156b1d57d14d056150e23735ee7adef45615390c9b5f17f85"},"schema_version":"1.0"},"canonical_sha256":"45d3e3ad6484adf15bd7b3242e84d25d29573cb35d326f9efde3772d74acc549","source":{"kind":"arxiv","id":"2309.15013","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15013","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15013v1","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15013","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"IXJ6HLLEQSW7","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"IXJ6HLLEQSW7CW6X","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"IXJ6HLLE","created_at":"2026-07-05T06:54:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IXJ6HLLEQSW7CW6XWMSC5BGSLU","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T15:32:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c38f79cc31971b7c397309310316838d3f268db911558e41891e45d5463660de","abstract_canon_sha256":"5e4784eac8a900b156b1d57d14d056150e23735ee7adef45615390c9b5f17f85"},"schema_version":"1.0"},"canonical_sha256":"45d3e3ad6484adf15bd7b3242e84d25d29573cb35d326f9efde3772d74acc549","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:32.754329Z","signature_b64":"RBFS52bpOCwTBJ3Hcqg/fqcs3A9gwqSo0JNCl3v8+gKSU9HrxqSLkGEHcejE2B/hdyoLVVEswlGX3vSVVSC+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45d3e3ad6484adf15bd7b3242e84d25d29573cb35d326f9efde3772d74acc549","last_reissued_at":"2026-07-05T06:54:32.753823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:32.753823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15013","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":"2026-07-05T06:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCFmAgdxrAE2QU500Ja7GLgexecDtYUSW9In4A+guCOKULmhNeva32hWpfHvG3ac9xkCOAbF9ye2S/2E0j/lAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:04:00.654253Z"},"content_sha256":"b44589f2303c15aca7a0d5b54123bf2b4a11447960c809e1a47577ddf6ddc090","schema_version":"1.0","event_id":"sha256:b44589f2303c15aca7a0d5b54123bf2b4a11447960c809e1a47577ddf6ddc090"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IXJ6HLLEQSW7CW6XWMSC5BGSLU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Updated Corpora and Benchmarks for Long-Form Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Corey Miller, Desh Raj, Jennifer Drexler Fox, Mig\\\"uel Jett\\'e, Natalie Delworth, Quinn McNamara","submitted_at":"2023-09-26T15:32:09Z","abstract_excerpt":"The vast majority of ASR research uses corpora in which both the training and test data have been pre-segmented into utterances. In most real-word ASR use-cases, however, test audio is not segmented, leading to a mismatch between inference-time conditions and models trained on segmented utterances. In this paper, we re-release three standard ASR corpora - TED-LIUM 3, Gigapeech, and VoxPopuli-en - with updated transcription and alignments to enable their use for long-form ASR research. We use these reconstituted corpora to study the train-test mismatch problem for transducers and attention-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15013","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/2309.15013/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":"2026-07-05T06:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MB0G4IQtqYZf9dMUk4zcBxHuaNPrfqBPL2C+TEmBSNCMEBek0sKqv03L4JC6d8PHIfp7LKqPyiNv5S83Drd+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:04:00.654634Z"},"content_sha256":"3b4ae83c8a90cee60af81c286881490ff204f542146ab07006851595da7824c3","schema_version":"1.0","event_id":"sha256:3b4ae83c8a90cee60af81c286881490ff204f542146ab07006851595da7824c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/bundle.json","state_url":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/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":"2026-08-21T18:04:00Z","links":{"resolver":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU","bundle":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/bundle.json","state":"https://pith.science/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXJ6HLLEQSW7CW6XWMSC5BGSLU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IXJ6HLLEQSW7CW6XWMSC5BGSLU","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":"5e4784eac8a900b156b1d57d14d056150e23735ee7adef45615390c9b5f17f85","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T15:32:09Z","title_canon_sha256":"c38f79cc31971b7c397309310316838d3f268db911558e41891e45d5463660de"},"schema_version":"1.0","source":{"id":"2309.15013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15013","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15013v1","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15013","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"IXJ6HLLEQSW7","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"IXJ6HLLEQSW7CW6X","created_at":"2026-07-05T06:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"IXJ6HLLE","created_at":"2026-07-05T06:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:3b4ae83c8a90cee60af81c286881490ff204f542146ab07006851595da7824c3","target":"graph","created_at":"2026-07-05T06:54:32Z","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/2309.15013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vast majority of ASR research uses corpora in which both the training and test data have been pre-segmented into utterances. In most real-word ASR use-cases, however, test audio is not segmented, leading to a mismatch between inference-time conditions and models trained on segmented utterances. In this paper, we re-release three standard ASR corpora - TED-LIUM 3, Gigapeech, and VoxPopuli-en - with updated transcription and alignments to enable their use for long-form ASR research. We use these reconstituted corpora to study the train-test mismatch problem for transducers and attention-base","authors_text":"Corey Miller, Desh Raj, Jennifer Drexler Fox, Mig\\\"uel Jett\\'e, Natalie Delworth, Quinn McNamara","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T15:32:09Z","title":"Updated Corpora and Benchmarks for Long-Form Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15013","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:b44589f2303c15aca7a0d5b54123bf2b4a11447960c809e1a47577ddf6ddc090","target":"record","created_at":"2026-07-05T06:54:32Z","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":"5e4784eac8a900b156b1d57d14d056150e23735ee7adef45615390c9b5f17f85","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T15:32:09Z","title_canon_sha256":"c38f79cc31971b7c397309310316838d3f268db911558e41891e45d5463660de"},"schema_version":"1.0","source":{"id":"2309.15013","kind":"arxiv","version":1}},"canonical_sha256":"45d3e3ad6484adf15bd7b3242e84d25d29573cb35d326f9efde3772d74acc549","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45d3e3ad6484adf15bd7b3242e84d25d29573cb35d326f9efde3772d74acc549","first_computed_at":"2026-07-05T06:54:32.753823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:32.753823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RBFS52bpOCwTBJ3Hcqg/fqcs3A9gwqSo0JNCl3v8+gKSU9HrxqSLkGEHcejE2B/hdyoLVVEswlGX3vSVVSC+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:32.754329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b44589f2303c15aca7a0d5b54123bf2b4a11447960c809e1a47577ddf6ddc090","sha256:3b4ae83c8a90cee60af81c286881490ff204f542146ab07006851595da7824c3"],"state_sha256":"12da53ad81ba2a2c406b3dd2f5e3a0f90c1f86a48f10ca1b3a5f7ba22ac6c421"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2fMvoCN27HzUqUJi2ZfbunadNGW2U/03AKvRrkQPNKUTLmfdvwuWbj614rCCRNJXYI9Ou2ZIYfuEfKuErv+jAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:04:00.657223Z","bundle_sha256":"d0eba526dbd49471826ee026c1e61aff432ecc222a0cf9c5d2ced5f96622b41b"}}