{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:O22JVZXXCDIP65NBPME3IDNOPV","short_pith_number":"pith:O22JVZXX","canonical_record":{"source":{"id":"2212.02782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-12-06T06:37:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"363268429dd685d2e01282b11ef294b9ca3172a83c5aac461a0634cecbf90c20","abstract_canon_sha256":"2e43db9806664a0ee00174050141104fec3fe6e2ca658d024af8c1534278c5e8"},"schema_version":"1.0"},"canonical_sha256":"76b49ae6f710d0ff75a17b09b40dae7d7646bcdb27ee335fad1b793a286c5411","source":{"kind":"arxiv","id":"2212.02782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.02782","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"2212.02782v1","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02782","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"O22JVZXXCDIP","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"O22JVZXXCDIP65NB","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"O22JVZXX","created_at":"2026-07-05T05:22:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:O22JVZXXCDIP65NBPME3IDNOPV","target":"record","payload":{"canonical_record":{"source":{"id":"2212.02782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-12-06T06:37:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"363268429dd685d2e01282b11ef294b9ca3172a83c5aac461a0634cecbf90c20","abstract_canon_sha256":"2e43db9806664a0ee00174050141104fec3fe6e2ca658d024af8c1534278c5e8"},"schema_version":"1.0"},"canonical_sha256":"76b49ae6f710d0ff75a17b09b40dae7d7646bcdb27ee335fad1b793a286c5411","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:34.216971Z","signature_b64":"meFX+XiwJ6c5gstzDv4mW4AzVgG8sGYiI8L9m4GZqyMBO+j/Go43ei2Tv8VT4/W5Dp65s/gfVUtY2bDcAoI9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76b49ae6f710d0ff75a17b09b40dae7d7646bcdb27ee335fad1b793a286c5411","last_reissued_at":"2026-07-05T05:22:34.216480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:34.216480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.02782","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:22:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WxLdcsTsikAv9Jn0miyLOh2x63lWv6qqpxF8IlEfaIJrpbxIVpVWrDzUv4waXrPIB0sfiJt0iiWt4C+4W/NvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:39:13.555795Z"},"content_sha256":"6c32517ba599eed2eb340c4edfdb80f2d8594ca0ef0665e698578be2d9e4f9f4","schema_version":"1.0","event_id":"sha256:6c32517ba599eed2eb340c4edfdb80f2d8594ca0ef0665e698578be2d9e4f9f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:O22JVZXXCDIP65NBPME3IDNOPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Liu, Genshun Wan, Jianqing Gao, Jia Pan, Jing-Xuan Zhang, Zhen-Hua Ling","submitted_at":"2022-12-06T06:37:38Z","abstract_excerpt":"In this work, we present a novel method, named AV2vec, for learning audio-visual speech representations by multimodal self-distillation. AV2vec has a student and a teacher module, in which the student performs a masked latent feature regression task using the multimodal target features generated online by the teacher. The parameters of the teacher model are a momentum update of the student. Since our target features are generated online, AV2vec needs no iteration step like AV-HuBERT and the total training time cost is reduced to less than one-fifth. We further propose AV2vec-MLM in this study,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02782","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/2212.02782/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:22:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QUAd3iZkZ7ogMlusiqnk2vagT/pGm0wx4jnqv9vuVq1BBnl87Zehd0icm+GlquPdp6oov086DuS/ocPxcGEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:39:13.556661Z"},"content_sha256":"5b79fa529b5282ea3fe950be3ff2333c86506085a19be8f7a96cae45db0ec5b2","schema_version":"1.0","event_id":"sha256:5b79fa529b5282ea3fe950be3ff2333c86506085a19be8f7a96cae45db0ec5b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/bundle.json","state_url":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O22JVZXXCDIP65NBPME3IDNOPV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T02:39:13Z","links":{"resolver":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV","bundle":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/bundle.json","state":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O22JVZXXCDIP65NBPME3IDNOPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O22JVZXXCDIP65NBPME3IDNOPV","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":"2e43db9806664a0ee00174050141104fec3fe6e2ca658d024af8c1534278c5e8","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-12-06T06:37:38Z","title_canon_sha256":"363268429dd685d2e01282b11ef294b9ca3172a83c5aac461a0634cecbf90c20"},"schema_version":"1.0","source":{"id":"2212.02782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.02782","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"2212.02782v1","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02782","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"O22JVZXXCDIP","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"O22JVZXXCDIP65NB","created_at":"2026-07-05T05:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"O22JVZXX","created_at":"2026-07-05T05:22:34Z"}],"graph_snapshots":[{"event_id":"sha256:5b79fa529b5282ea3fe950be3ff2333c86506085a19be8f7a96cae45db0ec5b2","target":"graph","created_at":"2026-07-05T05:22:34Z","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/2212.02782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present a novel method, named AV2vec, for learning audio-visual speech representations by multimodal self-distillation. AV2vec has a student and a teacher module, in which the student performs a masked latent feature regression task using the multimodal target features generated online by the teacher. The parameters of the teacher model are a momentum update of the student. Since our target features are generated online, AV2vec needs no iteration step like AV-HuBERT and the total training time cost is reduced to less than one-fifth. We further propose AV2vec-MLM in this study,","authors_text":"Cong Liu, Genshun Wan, Jianqing Gao, Jia Pan, Jing-Xuan Zhang, Zhen-Hua Ling","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-12-06T06:37:38Z","title":"Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02782","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":"sha256:6c32517ba599eed2eb340c4edfdb80f2d8594ca0ef0665e698578be2d9e4f9f4","target":"record","created_at":"2026-07-05T05:22:34Z","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":"2e43db9806664a0ee00174050141104fec3fe6e2ca658d024af8c1534278c5e8","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-12-06T06:37:38Z","title_canon_sha256":"363268429dd685d2e01282b11ef294b9ca3172a83c5aac461a0634cecbf90c20"},"schema_version":"1.0","source":{"id":"2212.02782","kind":"arxiv","version":1}},"canonical_sha256":"76b49ae6f710d0ff75a17b09b40dae7d7646bcdb27ee335fad1b793a286c5411","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76b49ae6f710d0ff75a17b09b40dae7d7646bcdb27ee335fad1b793a286c5411","first_computed_at":"2026-07-05T05:22:34.216480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:34.216480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"meFX+XiwJ6c5gstzDv4mW4AzVgG8sGYiI8L9m4GZqyMBO+j/Go43ei2Tv8VT4/W5Dp65s/gfVUtY2bDcAoI9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:34.216971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.02782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c32517ba599eed2eb340c4edfdb80f2d8594ca0ef0665e698578be2d9e4f9f4","sha256:5b79fa529b5282ea3fe950be3ff2333c86506085a19be8f7a96cae45db0ec5b2"],"state_sha256":"aad9a1987932a4d0a8736369914aecab815017fc8beb5e85cc22c6cbbc73b9d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WVXpoqt8w171YswlNrC4J/5vrTjfJlVtI+nKiIDlQTIhrdp7sq4PddBfU2luvmf8WmQtZYG0Skuu0kv2LHVJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:39:13.561542Z","bundle_sha256":"a536ad68a72fc248f03d5e5d35c386d717d8cd542778452d0013af1c7bd2bec6"}}