{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YR3WCAPXWXVNB5YPDRQFUJOMVL","short_pith_number":"pith:YR3WCAPX","schema_version":"1.0","canonical_sha256":"c4776101f7b5ead0f70f1c605a25ccaad019b0b7e371ef9953b8cceaf22102b8","source":{"kind":"arxiv","id":"2205.09872","version":2},"attestation_state":"computed","paper":{"title":"Content-Context Factorized Representations for Automated Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"David M. Chan, Shalini Ghosh","submitted_at":"2022-05-19T21:34:40Z","abstract_excerpt":"Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the spoken language content, but also may contain information about unnecessary contexts such as background noise and sounds or speaker identity, accent, or protected attributes. Such information can directly harm generalization performance, by introducing spurious correlations between the spoken words and the context in which such words were spoken. In this work, w"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.09872","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-19T21:34:40Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"ec98a5a69ff4e452055ba1b625732ff50a1af0c6d4c6c20f8e9bc9e74607034f","abstract_canon_sha256":"f047637eb80e781ed084c0fb469de587732b7b61b5d4addd9bfd5346107bb2e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:46.553270Z","signature_b64":"7Smk6bsO0GA3rIP9JCW0sQMofpxivkjmhuTkUk5XxYuUYHqvEL+8sBi/ETcrebsOcZzTn+YL0Ymo0CysWbR0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4776101f7b5ead0f70f1c605a25ccaad019b0b7e371ef9953b8cceaf22102b8","last_reissued_at":"2026-07-05T04:57:46.552869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:46.552869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Content-Context Factorized Representations for Automated Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"David M. Chan, Shalini Ghosh","submitted_at":"2022-05-19T21:34:40Z","abstract_excerpt":"Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the spoken language content, but also may contain information about unnecessary contexts such as background noise and sounds or speaker identity, accent, or protected attributes. Such information can directly harm generalization performance, by introducing spurious correlations between the spoken words and the context in which such words were spoken. In this work, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09872","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/2205.09872/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.09872","created_at":"2026-07-05T04:57:46.552925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09872v2","created_at":"2026-07-05T04:57:46.552925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09872","created_at":"2026-07-05T04:57:46.552925+00:00"},{"alias_kind":"pith_short_12","alias_value":"YR3WCAPXWXVN","created_at":"2026-07-05T04:57:46.552925+00:00"},{"alias_kind":"pith_short_16","alias_value":"YR3WCAPXWXVNB5YP","created_at":"2026-07-05T04:57:46.552925+00:00"},{"alias_kind":"pith_short_8","alias_value":"YR3WCAPX","created_at":"2026-07-05T04:57:46.552925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04266","citing_title":"Representation Purification for End-to-End Speech Translation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL","json":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL.json","graph_json":"https://pith.science/api/pith-number/YR3WCAPXWXVNB5YPDRQFUJOMVL/graph.json","events_json":"https://pith.science/api/pith-number/YR3WCAPXWXVNB5YPDRQFUJOMVL/events.json","paper":"https://pith.science/paper/YR3WCAPX"},"agent_actions":{"view_html":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL","download_json":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL.json","view_paper":"https://pith.science/paper/YR3WCAPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09872&json=true","fetch_graph":"https://pith.science/api/pith-number/YR3WCAPXWXVNB5YPDRQFUJOMVL/graph.json","fetch_events":"https://pith.science/api/pith-number/YR3WCAPXWXVNB5YPDRQFUJOMVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL/action/storage_attestation","attest_author":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL/action/author_attestation","sign_citation":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL/action/citation_signature","submit_replication":"https://pith.science/pith/YR3WCAPXWXVNB5YPDRQFUJOMVL/action/replication_record"}},"created_at":"2026-07-05T04:57:46.552925+00:00","updated_at":"2026-07-05T04:57:46.552925+00:00"}