{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VYQE5VFBS7VNTXIPWPWUQ5X64I","short_pith_number":"pith:VYQE5VFB","canonical_record":{"source":{"id":"2309.15796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-26T12:58:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"ccfa1d6b3eba0960568ba8bebccc0c2eac23f0cc464161247f888084fa6020e9","abstract_canon_sha256":"b12dfa9ec0eb84d2bf64c9f3891aff3c95f2fdbb65777830e40c268a0141d246"},"schema_version":"1.0"},"canonical_sha256":"ae204ed4a197ead9dd0fb3ed4876fee22ad6c16fa5887ca01c1667883f06480d","source":{"kind":"arxiv","id":"2309.15796","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15796","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15796v1","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15796","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"pith_short_12","alias_value":"VYQE5VFBS7VN","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"pith_short_16","alias_value":"VYQE5VFBS7VNTXIP","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"pith_short_8","alias_value":"VYQE5VFB","created_at":"2026-07-05T06:54:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VYQE5VFBS7VNTXIPWPWUQ5X64I","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-26T12:58:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"ccfa1d6b3eba0960568ba8bebccc0c2eac23f0cc464161247f888084fa6020e9","abstract_canon_sha256":"b12dfa9ec0eb84d2bf64c9f3891aff3c95f2fdbb65777830e40c268a0141d246"},"schema_version":"1.0"},"canonical_sha256":"ae204ed4a197ead9dd0fb3ed4876fee22ad6c16fa5887ca01c1667883f06480d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:57.604503Z","signature_b64":"KXRi5xOUwP4jZAR21WDN11M5Z6Fq13b3uYukgUunAgyOxjvOXew+t4g/6jSDX/AxUnKgftm9Yx8Yf8BRnzIrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae204ed4a197ead9dd0fb3ed4876fee22ad6c16fa5887ca01c1667883f06480d","last_reissued_at":"2026-07-05T06:54:57.603962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:57.603962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15796","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":"2026-07-05T06:54:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSBjyArjaq+f8KHHFrhkc7HzZ+XRRTLzx1vmWBnOhpWO0fZJLXEwtkcvUINKHvZCP97uu6HW39lefuezx32MCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:11:34.484028Z"},"content_sha256":"4271c0d8992bf817d7219148b85d7251dae66f8e41cbb20654c5df23d356daa7","schema_version":"1.0","event_id":"sha256:4271c0d8992bf817d7219148b85d7251dae66f8e41cbb20654c5df23d356daa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VYQE5VFBS7VNTXIPWPWUQ5X64I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Daniel Povey, Desh Raj, Dongji Gao, Hainan Xu, Leibny Paola Garcia Perera, Sanjeev Khudanpur","submitted_at":"2023-09-26T12:58:40Z","abstract_excerpt":"Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform \"non-verbatim\" transcription, which can result in poorly trained models. In this paper, we propose Omni-temporal Classification (OTC), a novel training criterion that explicitly incorporates label uncertainties originating from such weak supervision. This allows the model to effectively learn speech-text alignments while accommodating errors present in the training transcripts. OTC extends the conventional CTC objective for imperfect transcripts by l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15796","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/2309.15796/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":"2026-07-05T06:54:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5FOhY6ef0ev6lWTNN5dMvZ/ZUfKjyZpC89ijanrDBO/POa89JZf2yYGy/1Lruem4mX1iulvDuwouwpB1V3k+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:11:34.484411Z"},"content_sha256":"833fc1a9819f8edcd7df0910e8214f93c74a1fbaa9d19f33afa224e1a92fb862","schema_version":"1.0","event_id":"sha256:833fc1a9819f8edcd7df0910e8214f93c74a1fbaa9d19f33afa224e1a92fb862"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYQE5VFBS7VNTXIPWPWUQ5X64I/bundle.json","state_url":"https://pith.science/pith/VYQE5VFBS7VNTXIPWPWUQ5X64I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYQE5VFBS7VNTXIPWPWUQ5X64I/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":"2026-08-22T07:11:34Z","links":{"resolver":"https://pith.science/pith/VYQE5VFBS7VNTXIPWPWUQ5X64I","bundle":"https://pith.science/pith/VYQE5VFBS7VNTXIPWPWUQ5X64I/bundle.json","state":"https://pith.science/pith/VYQE5VFBS7VNTXIPWPWUQ5X64I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYQE5VFBS7VNTXIPWPWUQ5X64I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VYQE5VFBS7VNTXIPWPWUQ5X64I","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":"b12dfa9ec0eb84d2bf64c9f3891aff3c95f2fdbb65777830e40c268a0141d246","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-26T12:58:40Z","title_canon_sha256":"ccfa1d6b3eba0960568ba8bebccc0c2eac23f0cc464161247f888084fa6020e9"},"schema_version":"1.0","source":{"id":"2309.15796","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15796","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15796v1","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15796","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"pith_short_12","alias_value":"VYQE5VFBS7VN","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"pith_short_16","alias_value":"VYQE5VFBS7VNTXIP","created_at":"2026-07-05T06:54:57Z"},{"alias_kind":"pith_short_8","alias_value":"VYQE5VFB","created_at":"2026-07-05T06:54:57Z"}],"graph_snapshots":[{"event_id":"sha256:833fc1a9819f8edcd7df0910e8214f93c74a1fbaa9d19f33afa224e1a92fb862","target":"graph","created_at":"2026-07-05T06:54:57Z","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/2309.15796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform \"non-verbatim\" transcription, which can result in poorly trained models. In this paper, we propose Omni-temporal Classification (OTC), a novel training criterion that explicitly incorporates label uncertainties originating from such weak supervision. This allows the model to effectively learn speech-text alignments while accommodating errors present in the training transcripts. OTC extends the conventional CTC objective for imperfect transcripts by l","authors_text":"Daniel Povey, Desh Raj, Dongji Gao, Hainan Xu, Leibny Paola Garcia Perera, Sanjeev Khudanpur","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-26T12:58:40Z","title":"Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15796","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":"sha256:4271c0d8992bf817d7219148b85d7251dae66f8e41cbb20654c5df23d356daa7","target":"record","created_at":"2026-07-05T06:54:57Z","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":"b12dfa9ec0eb84d2bf64c9f3891aff3c95f2fdbb65777830e40c268a0141d246","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-26T12:58:40Z","title_canon_sha256":"ccfa1d6b3eba0960568ba8bebccc0c2eac23f0cc464161247f888084fa6020e9"},"schema_version":"1.0","source":{"id":"2309.15796","kind":"arxiv","version":1}},"canonical_sha256":"ae204ed4a197ead9dd0fb3ed4876fee22ad6c16fa5887ca01c1667883f06480d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae204ed4a197ead9dd0fb3ed4876fee22ad6c16fa5887ca01c1667883f06480d","first_computed_at":"2026-07-05T06:54:57.603962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:57.603962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXRi5xOUwP4jZAR21WDN11M5Z6Fq13b3uYukgUunAgyOxjvOXew+t4g/6jSDX/AxUnKgftm9Yx8Yf8BRnzIrCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:57.604503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15796","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4271c0d8992bf817d7219148b85d7251dae66f8e41cbb20654c5df23d356daa7","sha256:833fc1a9819f8edcd7df0910e8214f93c74a1fbaa9d19f33afa224e1a92fb862"],"state_sha256":"93eca76147f19b3d9bc9a5221db0765b5834115517eeb4f6b593fc2e5b89492d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKmI1qHB/cVF/znuKMdInixBpxe5Xt4c6OkwbHx5P8eC5VNR8mVMykzEaHODQBA3XCGzbvNoxOQ1L2rC7BDhBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:11:34.487078Z","bundle_sha256":"b484ad62e5f16af8681c26b7dd473531d3fe9dee5ffecf602c7df0395813e659"}}