{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ARUPKIJJIKJ6Y3NYWXG3SJRHKQ","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":"4e05e987ffd16772e6c3d7f7e565703618ac10efd99706d8bf7152844d1c63b7","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T17:35:16Z","title_canon_sha256":"029caab5f59b623a4395a292c676796495ce5c14292d1767834fd269b93c8eac"},"schema_version":"1.0","source":{"id":"2309.10787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10787","created_at":"2026-07-05T07:57:43Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10787v2","created_at":"2026-07-05T07:57:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10787","created_at":"2026-07-05T07:57:43Z"},{"alias_kind":"pith_short_12","alias_value":"ARUPKIJJIKJ6","created_at":"2026-07-05T07:57:43Z"},{"alias_kind":"pith_short_16","alias_value":"ARUPKIJJIKJ6Y3NY","created_at":"2026-07-05T07:57:43Z"},{"alias_kind":"pith_short_8","alias_value":"ARUPKIJJ","created_at":"2026-07-05T07:57:43Z"}],"graph_snapshots":[{"event_id":"sha256:baac2b87da3b28e9038ef1ff78403263787905153707befb75e36f917221c255","target":"graph","created_at":"2026-07-05T07:57:43Z","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/2309.10787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual representation learning aims to develop systems with human-like perception by utilizing correlation between auditory and visual information. However, current models often focus on a limited set of tasks, and generalization abilities of learned representations are unclear. To this end, we propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations on 7 datasets covering 5 audio-visual tasks in speech and audio processing. We evaluate 5 recent self-supervised models and show that none of these models generalize ","authors_text":"Abdelrahman Mohamed, Chi-Luen Feng, Chun-Mao Lai, David Harwath, Haibin Wu, Hsuan-Hao Lin, Hung-yi Lee, Hung-Yu Wang, I-Hsiang Chiu, Layne Berry, Max Liu, Po-Yao Huang, Puyuan Peng, Shang-Wen Li, Shinji Watanabe, Yi-Jen Shih, Yi-Ting Chen, Yuan Tseng, Yu Tsao","cross_cats":["cs.CV","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T17:35:16Z","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10787","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":"sha256:316c2b06dbdce6cc91767b15836534cd50f7e0afb9a666da4dca62b8063249d9","target":"record","created_at":"2026-07-05T07:57:43Z","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":"4e05e987ffd16772e6c3d7f7e565703618ac10efd99706d8bf7152844d1c63b7","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T17:35:16Z","title_canon_sha256":"029caab5f59b623a4395a292c676796495ce5c14292d1767834fd269b93c8eac"},"schema_version":"1.0","source":{"id":"2309.10787","kind":"arxiv","version":2}},"canonical_sha256":"0468f521294293ec6db8b5cdb92627543fcad778163f1581be01894e2901dcca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0468f521294293ec6db8b5cdb92627543fcad778163f1581be01894e2901dcca","first_computed_at":"2026-07-05T07:57:43.858158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:43.858158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"31z0CkNXw4r7jGbCkkfQIeSUa5/DRediP+fwrAHW29RdVL2KNN5sCH7nojGar8/y2i0vakRibLg85M/2ta8VCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:43.858773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:316c2b06dbdce6cc91767b15836534cd50f7e0afb9a666da4dca62b8063249d9","sha256:baac2b87da3b28e9038ef1ff78403263787905153707befb75e36f917221c255"],"state_sha256":"a218deafa22d04bc1b2bf9eb34006895cfa5a4cedd2fa572a67986ab47513a7e"}