{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SKZUFTR2IV5UJOQNIOGZ3FB4I4","short_pith_number":"pith:SKZUFTR2","canonical_record":{"source":{"id":"2309.13876","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-25T05:01:34Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"04cf60d5b4a2d7158d3223dcdf3b60c6cbf292cbdc357c6bb883444bd2026062","abstract_canon_sha256":"8ff5c471fb7128f13020c6ec042c3de9c695265c3ee2d6e5a3ec010a64b20057"},"schema_version":"1.0"},"canonical_sha256":"92b342ce3a457b44ba0d438d9d943c473b1c5bc13c3aac4447a73918f2c55e09","source":{"kind":"arxiv","id":"2309.13876","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13876","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13876v3","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13876","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"SKZUFTR2IV5U","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"SKZUFTR2IV5UJOQN","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"SKZUFTR2","created_at":"2026-07-05T07:04:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SKZUFTR2IV5UJOQNIOGZ3FB4I4","target":"record","payload":{"canonical_record":{"source":{"id":"2309.13876","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-25T05:01:34Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"04cf60d5b4a2d7158d3223dcdf3b60c6cbf292cbdc357c6bb883444bd2026062","abstract_canon_sha256":"8ff5c471fb7128f13020c6ec042c3de9c695265c3ee2d6e5a3ec010a64b20057"},"schema_version":"1.0"},"canonical_sha256":"92b342ce3a457b44ba0d438d9d943c473b1c5bc13c3aac4447a73918f2c55e09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:51.002570Z","signature_b64":"LlKEan1kn2InOZfNYwXgnaPw7eILSkbCrJk0cKF9kIXVQbQiUu+2NUI4JrbGFWOd/gJrhggOUrVOhNRDjk4sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92b342ce3a457b44ba0d438d9d943c473b1c5bc13c3aac4447a73918f2c55e09","last_reissued_at":"2026-07-05T07:04:51.002077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:51.002077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.13876","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7VERo4GRtF9cvUSa7begnhQdGT0KprQuh0aPPn7koo7Ej0mnQicZhI3hSsXHv29/kESsaXXXBd/PO8U2yZmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:16:27.796609Z"},"content_sha256":"89c61eac4f269df21b0a0ff445d1460320caeb3f83a7bf90106e50c189ed0030","schema_version":"1.0","event_id":"sha256:89c61eac4f269df21b0a0ff445d1460320caeb3f83a7bf90106e50c189ed0030"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SKZUFTR2IV5UJOQNIOGZ3FB4I4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Yan, Dan Berrebbi, Jee-weon Jung, Jiatong Shi, Jinchuan Tian, Muhammad Shakeel, Roshan Sharma, Shinji Watanabe, Siddhant Arora, Soumi Maiti, Wangyou Zhang, William Chen, Xinjian Li, Xuankai Chang, Yifan Peng, Yui Sudo","submitted_at":"2023-09-25T05:01:34Z","abstract_excerpt":"Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data. It generalizes well to various speech recognition and translation benchmarks even in a zero-shot setup. However, the full pipeline for developing such models (from data collection to training) is not publicly accessible, which makes it difficult for researchers to further improve its performance and address training-related issues such as efficiency, robustness, fairness, and bias. This work presents an Open Whisp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13876","kind":"arxiv","version":3},"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/2309.13876/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":"2026-07-05T07:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Ncd0xQ4NnWX38IoTu4NHGBX8ab2IeBU+Qq/0bZd5mRKJPcW4MgWgHeEcURYyHA7f37imR0CR4/QmNF7uCrwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:16:27.797125Z"},"content_sha256":"01735ddabb846455576a9fa24e20b158ad4218a555d3e1609a414ea9401e7c8c","schema_version":"1.0","event_id":"sha256:01735ddabb846455576a9fa24e20b158ad4218a555d3e1609a414ea9401e7c8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKZUFTR2IV5UJOQNIOGZ3FB4I4/bundle.json","state_url":"https://pith.science/pith/SKZUFTR2IV5UJOQNIOGZ3FB4I4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKZUFTR2IV5UJOQNIOGZ3FB4I4/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":"2026-08-22T05:16:27Z","links":{"resolver":"https://pith.science/pith/SKZUFTR2IV5UJOQNIOGZ3FB4I4","bundle":"https://pith.science/pith/SKZUFTR2IV5UJOQNIOGZ3FB4I4/bundle.json","state":"https://pith.science/pith/SKZUFTR2IV5UJOQNIOGZ3FB4I4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKZUFTR2IV5UJOQNIOGZ3FB4I4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SKZUFTR2IV5UJOQNIOGZ3FB4I4","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":"8ff5c471fb7128f13020c6ec042c3de9c695265c3ee2d6e5a3ec010a64b20057","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-25T05:01:34Z","title_canon_sha256":"04cf60d5b4a2d7158d3223dcdf3b60c6cbf292cbdc357c6bb883444bd2026062"},"schema_version":"1.0","source":{"id":"2309.13876","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13876","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13876v3","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13876","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"SKZUFTR2IV5U","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"SKZUFTR2IV5UJOQN","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"SKZUFTR2","created_at":"2026-07-05T07:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:01735ddabb846455576a9fa24e20b158ad4218a555d3e1609a414ea9401e7c8c","target":"graph","created_at":"2026-07-05T07:04:51Z","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/2309.13876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data. It generalizes well to various speech recognition and translation benchmarks even in a zero-shot setup. However, the full pipeline for developing such models (from data collection to training) is not publicly accessible, which makes it difficult for researchers to further improve its performance and address training-related issues such as efficiency, robustness, fairness, and bias. This work presents an Open Whisp","authors_text":"Brian Yan, Dan Berrebbi, Jee-weon Jung, Jiatong Shi, Jinchuan Tian, Muhammad Shakeel, Roshan Sharma, Shinji Watanabe, Siddhant Arora, Soumi Maiti, Wangyou Zhang, William Chen, Xinjian Li, Xuankai Chang, Yifan Peng, Yui Sudo","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-25T05:01:34Z","title":"Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13876","kind":"arxiv","version":3},"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":"sha256:89c61eac4f269df21b0a0ff445d1460320caeb3f83a7bf90106e50c189ed0030","target":"record","created_at":"2026-07-05T07:04:51Z","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":"8ff5c471fb7128f13020c6ec042c3de9c695265c3ee2d6e5a3ec010a64b20057","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-25T05:01:34Z","title_canon_sha256":"04cf60d5b4a2d7158d3223dcdf3b60c6cbf292cbdc357c6bb883444bd2026062"},"schema_version":"1.0","source":{"id":"2309.13876","kind":"arxiv","version":3}},"canonical_sha256":"92b342ce3a457b44ba0d438d9d943c473b1c5bc13c3aac4447a73918f2c55e09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92b342ce3a457b44ba0d438d9d943c473b1c5bc13c3aac4447a73918f2c55e09","first_computed_at":"2026-07-05T07:04:51.002077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:51.002077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LlKEan1kn2InOZfNYwXgnaPw7eILSkbCrJk0cKF9kIXVQbQiUu+2NUI4JrbGFWOd/gJrhggOUrVOhNRDjk4sDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:51.002570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13876","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89c61eac4f269df21b0a0ff445d1460320caeb3f83a7bf90106e50c189ed0030","sha256:01735ddabb846455576a9fa24e20b158ad4218a555d3e1609a414ea9401e7c8c"],"state_sha256":"ab6c49bced11e2e1e22e90875b3abafa6b6401e297bfbc19c44b01170e0f9b0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KvO3o6RLo0LXz9T+KTSgCHyxsVxhXfTu7xa13qJPhyB3EeHuK6ScpqU+KPR1kKqR3VUqWARiu2X0Q1M1yEOjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:16:27.801369Z","bundle_sha256":"d1903556f139035ace0a5ff29e9b9a1700eab93e5f3c543b6d1b54080c926d56"}}