{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VO2Z3BTCKNJUURRZN2C2YDAWQU","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":"66a0b9ccf412f0098239517f5ad95bb22ac2580b60956fb9fd3d4ec39fc408f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-26T19:57:40Z","title_canon_sha256":"506f7c9d65e677c0c5640bb21a64e89a11e2bcdcc8dcee169759ba8605d47881"},"schema_version":"1.0","source":{"id":"2411.17846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17846","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17846v1","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17846","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"VO2Z3BTCKNJU","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"VO2Z3BTCKNJUURRZ","created_at":"2026-07-05T09:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"VO2Z3BTC","created_at":"2026-07-05T09:41:07Z"}],"graph_snapshots":[{"event_id":"sha256:e5ef5ba4125eebcd89e7a1a0ebf7c9930a7c46a4d326ef96ae7b34c4577b0a9d","target":"graph","created_at":"2026-07-05T09:41:07Z","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/2411.17846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the explainable Disentangled-Transformer, which disentangles the internal representations into sub-embeddings with explicit content and speaker traits based on varying temporal resolutions. Experimental results show that the proposed Disentangled-Transformer produces a clear speaker identity, separated from the speech content, for speaker diarization while improvi","authors_text":"Hugo Van hamme, Pu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-26T19:57:40Z","title":"Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17846","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":"sha256:4c0c37f319a129955eb6d421cc020ff33a6aaeccde8dd5430ac0729e06ce6e25","target":"record","created_at":"2026-07-05T09:41:07Z","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":"66a0b9ccf412f0098239517f5ad95bb22ac2580b60956fb9fd3d4ec39fc408f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-26T19:57:40Z","title_canon_sha256":"506f7c9d65e677c0c5640bb21a64e89a11e2bcdcc8dcee169759ba8605d47881"},"schema_version":"1.0","source":{"id":"2411.17846","kind":"arxiv","version":1}},"canonical_sha256":"abb59d866253534a46396e85ac0c16851007dc09aee4d4f87205aeab1364256c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abb59d866253534a46396e85ac0c16851007dc09aee4d4f87205aeab1364256c","first_computed_at":"2026-07-05T09:41:07.801065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:07.801065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"25bU2OZcWqoCsBNyu5Zwwctr2Qg581f7gWan7m9QBXR8Qq6IMANEePmfg835B2vG/05jJUrLqiJylDhDh972Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:07.801508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c0c37f319a129955eb6d421cc020ff33a6aaeccde8dd5430ac0729e06ce6e25","sha256:e5ef5ba4125eebcd89e7a1a0ebf7c9930a7c46a4d326ef96ae7b34c4577b0a9d"],"state_sha256":"53bb38089a0b871ff7d27c1ef800e284ad688d0f9a987046298473b2bd936bc7"}