{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZXDBTPFWO57IZGW6XNTQ7YV6OR","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":"16e1498c80f29741fe517e63f2af951188060fa7c7d7fb7e8e7193859c4ae03f","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-08T14:07:06Z","title_canon_sha256":"c60546038ad8036ad42c2f13ccd3650b6f01ddd4d86420108237c7c794ce2647"},"schema_version":"1.0","source":{"id":"2007.04134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.04134","created_at":"2026-07-05T01:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2007.04134v1","created_at":"2026-07-05T01:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04134","created_at":"2026-07-05T01:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZXDBTPFWO57I","created_at":"2026-07-05T01:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZXDBTPFWO57IZGW6","created_at":"2026-07-05T01:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZXDBTPFW","created_at":"2026-07-05T01:18:04Z"}],"graph_snapshots":[{"event_id":"sha256:212cfda406d29779c49741647ac04005995295d4cced0d20601842136f7ba882","target":"graph","created_at":"2026-07-05T01:18:04Z","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/2007.04134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from au","authors_text":"Abhinav Shukla, Maja Pantic, Stavros Petridis","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-08T14:07:06Z","title":"Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04134","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":"sha256:02db0e6d598123292d8cf5bd92130934ff7e9df691ac30ee314e0a9264720b90","target":"record","created_at":"2026-07-05T01:18:04Z","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":"16e1498c80f29741fe517e63f2af951188060fa7c7d7fb7e8e7193859c4ae03f","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-08T14:07:06Z","title_canon_sha256":"c60546038ad8036ad42c2f13ccd3650b6f01ddd4d86420108237c7c794ce2647"},"schema_version":"1.0","source":{"id":"2007.04134","kind":"arxiv","version":1}},"canonical_sha256":"cdc619bcb6777e8c9adebb670fe2be744ff4ad32961d92b04b9d829cfb6e708e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdc619bcb6777e8c9adebb670fe2be744ff4ad32961d92b04b9d829cfb6e708e","first_computed_at":"2026-07-05T01:18:04.807132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:04.807132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Pc/sQdj+bgGKW6jApk5KBoX4KpgP2oW/OOJ9x4bIPCNWuSFKpDNQumTqC9JpgoO9MF7LDuRg5Ir8NYl7JaLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:04.807535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.04134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02db0e6d598123292d8cf5bd92130934ff7e9df691ac30ee314e0a9264720b90","sha256:212cfda406d29779c49741647ac04005995295d4cced0d20601842136f7ba882"],"state_sha256":"2d76615f2f533dad4c55270917e0dc779b5af31b98c399af5361abab23c1877c"}