{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FRADWVQT3ZW6U7UPZK2H3PD6NI","short_pith_number":"pith:FRADWVQT","canonical_record":{"source":{"id":"2508.19990","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T15:48:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"76290f6702d96a0ac0c2c4e68497f247b8d2f5f230859ccfbc08084f33384fd3","abstract_canon_sha256":"dbc980a7ceae076dc5efc9a0219f036a1aa48701ba8c9fe160c3edc0c09e267f"},"schema_version":"1.0"},"canonical_sha256":"2c403b5613de6dea7e8fcab47dbc7e6a2d437cd4f1a277ba0e59be7c39bbad66","source":{"kind":"arxiv","id":"2508.19990","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19990","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19990v2","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19990","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"FRADWVQT3ZW6","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"FRADWVQT3ZW6U7UP","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"FRADWVQT","created_at":"2026-07-05T12:07:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FRADWVQT3ZW6U7UPZK2H3PD6NI","target":"record","payload":{"canonical_record":{"source":{"id":"2508.19990","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T15:48:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"76290f6702d96a0ac0c2c4e68497f247b8d2f5f230859ccfbc08084f33384fd3","abstract_canon_sha256":"dbc980a7ceae076dc5efc9a0219f036a1aa48701ba8c9fe160c3edc0c09e267f"},"schema_version":"1.0"},"canonical_sha256":"2c403b5613de6dea7e8fcab47dbc7e6a2d437cd4f1a277ba0e59be7c39bbad66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:10.987299Z","signature_b64":"qhJkgqDY+YeNNOP/wRZtX0h/8F2eVGISBR/MhcO3OWIdjS0zp1fviQRvPz6j7H6Js3J2XcoOpdy136FBflrfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c403b5613de6dea7e8fcab47dbc7e6a2d437cd4f1a277ba0e59be7c39bbad66","last_reissued_at":"2026-07-05T12:07:10.986925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:10.986925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.19990","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKNL+ZxRMIIAkJ5Z/b/tdfk0mfaWqOkQzfkiZUTt1N2w8SbNEydVkUFLHeNAsyQtZQqdECxpSH6iKIt+XHa0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:14:10.885900Z"},"content_sha256":"72a933c39fd07245b17676b604f0ea97101a714c9396ec535e532f1b5f399933","schema_version":"1.0","event_id":"sha256:72a933c39fd07245b17676b604f0ea97101a714c9396ec535e532f1b5f399933"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FRADWVQT3ZW6U7UPZK2H3PD6NI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heterogeneous Self-Supervised Acoustic Pre-Training with Local Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"A F M Saif, Brian Kingsbury, Tianyi Chen, Xiaodong Cui","submitted_at":"2025-08-27T15:48:50Z","abstract_excerpt":"Self-supervised pre-training using unlabeled data is widely used in automatic speech recognition. In this paper, we propose a new self-supervised pre-training approach to dealing with heterogeneous data. Instead of mixing all the data and minimizing the averaged global loss in the conventional way, we impose additional local constraints to ensure that the model optimizes each source of heterogeneous data to its local optimum after $K$-step gradient descent initialized from the model. We formulate this as a bilevel optimization problem, and use the first-order approximation method to solve the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19990","kind":"arxiv","version":2},"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/2508.19990/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":"2026-07-05T12:07:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hY6RpPPrGQ/3QaMYq8LQ9XXL/S6V3fPUyvyVrO5cuB2WB4xfHOEZm1TRQEEIEkMufA5le86oRCm+QN2coIX2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:14:10.886739Z"},"content_sha256":"715b679506688a9c540548771a2a19ac41b0eba15354439e47479dd4e63e13dd","schema_version":"1.0","event_id":"sha256:715b679506688a9c540548771a2a19ac41b0eba15354439e47479dd4e63e13dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRADWVQT3ZW6U7UPZK2H3PD6NI/bundle.json","state_url":"https://pith.science/pith/FRADWVQT3ZW6U7UPZK2H3PD6NI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRADWVQT3ZW6U7UPZK2H3PD6NI/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":"2026-08-19T23:14:10Z","links":{"resolver":"https://pith.science/pith/FRADWVQT3ZW6U7UPZK2H3PD6NI","bundle":"https://pith.science/pith/FRADWVQT3ZW6U7UPZK2H3PD6NI/bundle.json","state":"https://pith.science/pith/FRADWVQT3ZW6U7UPZK2H3PD6NI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRADWVQT3ZW6U7UPZK2H3PD6NI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FRADWVQT3ZW6U7UPZK2H3PD6NI","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":"dbc980a7ceae076dc5efc9a0219f036a1aa48701ba8c9fe160c3edc0c09e267f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T15:48:50Z","title_canon_sha256":"76290f6702d96a0ac0c2c4e68497f247b8d2f5f230859ccfbc08084f33384fd3"},"schema_version":"1.0","source":{"id":"2508.19990","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19990","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19990v2","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19990","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"FRADWVQT3ZW6","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"FRADWVQT3ZW6U7UP","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"FRADWVQT","created_at":"2026-07-05T12:07:10Z"}],"graph_snapshots":[{"event_id":"sha256:715b679506688a9c540548771a2a19ac41b0eba15354439e47479dd4e63e13dd","target":"graph","created_at":"2026-07-05T12:07:10Z","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/2508.19990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised pre-training using unlabeled data is widely used in automatic speech recognition. In this paper, we propose a new self-supervised pre-training approach to dealing with heterogeneous data. Instead of mixing all the data and minimizing the averaged global loss in the conventional way, we impose additional local constraints to ensure that the model optimizes each source of heterogeneous data to its local optimum after $K$-step gradient descent initialized from the model. We formulate this as a bilevel optimization problem, and use the first-order approximation method to solve the ","authors_text":"A F M Saif, Brian Kingsbury, Tianyi Chen, Xiaodong Cui","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T15:48:50Z","title":"Heterogeneous Self-Supervised Acoustic Pre-Training with Local Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19990","kind":"arxiv","version":2},"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":"sha256:72a933c39fd07245b17676b604f0ea97101a714c9396ec535e532f1b5f399933","target":"record","created_at":"2026-07-05T12:07:10Z","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":"dbc980a7ceae076dc5efc9a0219f036a1aa48701ba8c9fe160c3edc0c09e267f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T15:48:50Z","title_canon_sha256":"76290f6702d96a0ac0c2c4e68497f247b8d2f5f230859ccfbc08084f33384fd3"},"schema_version":"1.0","source":{"id":"2508.19990","kind":"arxiv","version":2}},"canonical_sha256":"2c403b5613de6dea7e8fcab47dbc7e6a2d437cd4f1a277ba0e59be7c39bbad66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c403b5613de6dea7e8fcab47dbc7e6a2d437cd4f1a277ba0e59be7c39bbad66","first_computed_at":"2026-07-05T12:07:10.986925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:10.986925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qhJkgqDY+YeNNOP/wRZtX0h/8F2eVGISBR/MhcO3OWIdjS0zp1fviQRvPz6j7H6Js3J2XcoOpdy136FBflrfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:10.987299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.19990","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72a933c39fd07245b17676b604f0ea97101a714c9396ec535e532f1b5f399933","sha256:715b679506688a9c540548771a2a19ac41b0eba15354439e47479dd4e63e13dd"],"state_sha256":"b86c87b3d6c8d8402c31bc1d8729a1508429ad8ca0e68cb7985f573ca428b761"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qC1wL4wQdYTDYdSqfjY4BTJw5PId3KLVo/rhJIYkDrnifegYtFmBnMxCIt6fTuAhcpRkse8bVF8BVlgY4t4AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:14:10.894493Z","bundle_sha256":"997206619b68a106bde52bc7d7b397446e4e738162f4f0759b7289a9005ad415"}}