{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BQ2R6I6BIYAGXPEE5KJIK2G5F7","short_pith_number":"pith:BQ2R6I6B","schema_version":"1.0","canonical_sha256":"0c351f23c146006bbc84ea928568dd2fdd0e35428f1b2d95b0454450c685ab74","source":{"kind":"arxiv","id":"2606.07259","version":1},"attestation_state":"computed","paper":{"title":"Assessing True Generalisability of Audio-Visual Speech Recognisers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Maja Pantic, Naomi Harte, Stavros Petridis, Zhaofeng Lin","submitted_at":"2026-06-05T13:35:10Z","abstract_excerpt":"Current Audio-Visual Speech Recognition (AVSR) models achieve near-perfect performance on the standard LRS3 benchmark, raising concerns of adaptive overfitting. To systematically assess true generalisability, we construct a highly controlled, unseen evaluation set subsampled from the massive MultiVSR dataset. Unlike standard out-of-distribution benchmarks, our subset strictly matches the acoustic, visual, and demographic distributions of the LRS3 test set. Evaluating five state-of-the-art architectures reveals a universal performance collapse, proving that current systems fail to generalise ev"},"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":"2606.07259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-05T13:35:10Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1a5add6b34901866cae87a4cda76cf91b7a8982b039e68e463fc72576e753af9","abstract_canon_sha256":"0db0429ad8cf6acda082d5a5ab966a8e880d3f2c669bef77ed3af261e244f50a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:16.328786Z","signature_b64":"/oAcLlkbJxOwaFpm2sVXIFqQ9W40jX4SH+YmMVgSEwVcNNaaSr4J/QOysGpFEVKfAOeV1RsS1UXJD4U4GnmABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c351f23c146006bbc84ea928568dd2fdd0e35428f1b2d95b0454450c685ab74","last_reissued_at":"2026-06-08T01:05:16.327688Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:16.327688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing True Generalisability of Audio-Visual Speech Recognisers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Maja Pantic, Naomi Harte, Stavros Petridis, Zhaofeng Lin","submitted_at":"2026-06-05T13:35:10Z","abstract_excerpt":"Current Audio-Visual Speech Recognition (AVSR) models achieve near-perfect performance on the standard LRS3 benchmark, raising concerns of adaptive overfitting. To systematically assess true generalisability, we construct a highly controlled, unseen evaluation set subsampled from the massive MultiVSR dataset. Unlike standard out-of-distribution benchmarks, our subset strictly matches the acoustic, visual, and demographic distributions of the LRS3 test set. Evaluating five state-of-the-art architectures reveals a universal performance collapse, proving that current systems fail to generalise ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07259","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/2606.07259/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":"2606.07259","created_at":"2026-06-08T01:05:16.327883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07259v1","created_at":"2026-06-08T01:05:16.327883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07259","created_at":"2026-06-08T01:05:16.327883+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQ2R6I6BIYAG","created_at":"2026-06-08T01:05:16.327883+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQ2R6I6BIYAGXPEE","created_at":"2026-06-08T01:05:16.327883+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQ2R6I6B","created_at":"2026-06-08T01:05:16.327883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7","json":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7.json","graph_json":"https://pith.science/api/pith-number/BQ2R6I6BIYAGXPEE5KJIK2G5F7/graph.json","events_json":"https://pith.science/api/pith-number/BQ2R6I6BIYAGXPEE5KJIK2G5F7/events.json","paper":"https://pith.science/paper/BQ2R6I6B"},"agent_actions":{"view_html":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7","download_json":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7.json","view_paper":"https://pith.science/paper/BQ2R6I6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07259&json=true","fetch_graph":"https://pith.science/api/pith-number/BQ2R6I6BIYAGXPEE5KJIK2G5F7/graph.json","fetch_events":"https://pith.science/api/pith-number/BQ2R6I6BIYAGXPEE5KJIK2G5F7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7/action/storage_attestation","attest_author":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7/action/author_attestation","sign_citation":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7/action/citation_signature","submit_replication":"https://pith.science/pith/BQ2R6I6BIYAGXPEE5KJIK2G5F7/action/replication_record"}},"created_at":"2026-06-08T01:05:16.327883+00:00","updated_at":"2026-06-08T01:05:16.327883+00:00"}