{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FS5JKWAIZ2TB6DYIFWLFTJ5UBD","short_pith_number":"pith:FS5JKWAI","schema_version":"1.0","canonical_sha256":"2cba955808cea61f0f082d9659a7b408fa83863c88f50d479b17f3c20f226941","source":{"kind":"arxiv","id":"2506.20361","version":1},"attestation_state":"computed","paper":{"title":"The role of audio-visual integration in the time course of phonetic encoding in self-supervised speech models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Oli Danyi Liu, Peter Bell, Yi Wang","submitted_at":"2025-06-25T12:23:12Z","abstract_excerpt":"Human speech perception is multimodal. In natural speech, lip movements can precede corresponding voicing by a non-negligible gap of 100-300 ms, especially for specific consonants, affecting the time course of neural phonetic encoding in human listeners. However, it remains unexplored whether self-supervised learning models, which have been used to simulate audio-visual integration in humans, can capture this asynchronicity between audio and visual cues. We compared AV-HuBERT, an audio-visual model, with audio-only HuBERT, by using linear classifiers to track their phonetic decodability over t"},"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":"2506.20361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-25T12:23:12Z","cross_cats_sorted":["cs.SD","eess.IV"],"title_canon_sha256":"265b7bfe48ce98d926b6966f03ba4bed1058270e5e8bbe23ec0c768b4cfd98b2","abstract_canon_sha256":"2867c1abb31bb4bab045f5431c37f6f906f181ad294a53297f0d4b09c1686fea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:04.255283Z","signature_b64":"DbOvh6Dhh/3pJp/grMqK1nbExqgmvX+a92U5CbhzFByLbxjmqW5V4lPrWcqNAGad50fWFSUDkag84lw9L7TJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cba955808cea61f0f082d9659a7b408fa83863c88f50d479b17f3c20f226941","last_reissued_at":"2026-07-05T11:27:04.254710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:04.254710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The role of audio-visual integration in the time course of phonetic encoding in self-supervised speech models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Oli Danyi Liu, Peter Bell, Yi Wang","submitted_at":"2025-06-25T12:23:12Z","abstract_excerpt":"Human speech perception is multimodal. In natural speech, lip movements can precede corresponding voicing by a non-negligible gap of 100-300 ms, especially for specific consonants, affecting the time course of neural phonetic encoding in human listeners. However, it remains unexplored whether self-supervised learning models, which have been used to simulate audio-visual integration in humans, can capture this asynchronicity between audio and visual cues. We compared AV-HuBERT, an audio-visual model, with audio-only HuBERT, by using linear classifiers to track their phonetic decodability over t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20361","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/2506.20361/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":"2506.20361","created_at":"2026-07-05T11:27:04.254769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20361v1","created_at":"2026-07-05T11:27:04.254769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20361","created_at":"2026-07-05T11:27:04.254769+00:00"},{"alias_kind":"pith_short_12","alias_value":"FS5JKWAIZ2TB","created_at":"2026-07-05T11:27:04.254769+00:00"},{"alias_kind":"pith_short_16","alias_value":"FS5JKWAIZ2TB6DYI","created_at":"2026-07-05T11:27:04.254769+00:00"},{"alias_kind":"pith_short_8","alias_value":"FS5JKWAI","created_at":"2026-07-05T11:27:04.254769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20361","citing_title":"The role of audio-visual integration in the time course of phonetic encoding in self-supervised speech models","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD","json":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD.json","graph_json":"https://pith.science/api/pith-number/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/graph.json","events_json":"https://pith.science/api/pith-number/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/events.json","paper":"https://pith.science/paper/FS5JKWAI"},"agent_actions":{"view_html":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD","download_json":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD.json","view_paper":"https://pith.science/paper/FS5JKWAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20361&json=true","fetch_graph":"https://pith.science/api/pith-number/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/graph.json","fetch_events":"https://pith.science/api/pith-number/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/action/storage_attestation","attest_author":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/action/author_attestation","sign_citation":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/action/citation_signature","submit_replication":"https://pith.science/pith/FS5JKWAIZ2TB6DYIFWLFTJ5UBD/action/replication_record"}},"created_at":"2026-07-05T11:27:04.254769+00:00","updated_at":"2026-07-05T11:27:04.254769+00:00"}