{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HFUC5MYKO2LCRLCWTDS5T34TVR","short_pith_number":"pith:HFUC5MYK","canonical_record":{"source":{"id":"2203.07996","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-24T15:12:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"912f4396d7c71458c26d1b2874298729317fd1d0eb2fce3f71bb784416743662","abstract_canon_sha256":"80c9c19439b6e735a4457db771d111a4a7f4b733a972419a6ba316fe13ceb809"},"schema_version":"1.0"},"canonical_sha256":"39682eb30a769628ac5698e5d9ef93ac787fe4d21bf4303b43152dac4a22aad7","source":{"kind":"arxiv","id":"2203.07996","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.07996","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"arxiv_version","alias_value":"2203.07996v2","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07996","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"pith_short_12","alias_value":"HFUC5MYKO2LC","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"pith_short_16","alias_value":"HFUC5MYKO2LCRLCW","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"pith_short_8","alias_value":"HFUC5MYK","created_at":"2026-07-05T04:08:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HFUC5MYKO2LCRLCWTDS5T34TVR","target":"record","payload":{"canonical_record":{"source":{"id":"2203.07996","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-24T15:12:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"912f4396d7c71458c26d1b2874298729317fd1d0eb2fce3f71bb784416743662","abstract_canon_sha256":"80c9c19439b6e735a4457db771d111a4a7f4b733a972419a6ba316fe13ceb809"},"schema_version":"1.0"},"canonical_sha256":"39682eb30a769628ac5698e5d9ef93ac787fe4d21bf4303b43152dac4a22aad7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:42.986268Z","signature_b64":"SR9GUYOqGkKYNajYGKy10kO5bprgNcBI6dqFo8nR5JPUYPShCpf8zZa4mzhkX/m/bVmRqNcMxh02vFW0PKZ4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39682eb30a769628ac5698e5d9ef93ac787fe4d21bf4303b43152dac4a22aad7","last_reissued_at":"2026-07-05T04:08:42.985917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:42.985917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.07996","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLMrPcnYSWj/cOy7Irx8+4/j4CcTSrsDqAZw/hW1hmc258yYivWirVYIAcc47uODvqMal8y6j51tDGPTza6XDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:50:34.147626Z"},"content_sha256":"c80f9ae4f55783dfec7d87957ab5e39b8ab790292e80594531cc5cdf1af34bbc","schema_version":"1.0","event_id":"sha256:c80f9ae4f55783dfec7d87957ab5e39b8ab790292e80594531cc5cdf1af34bbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HFUC5MYKO2LCRLCWTDS5T34TVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Helong Zhou, Peiyu Chen, Xichen Pan, Xinbing Wang, Yichen Gong, Zhouhan Lin","submitted_at":"2022-02-24T15:12:17Z","abstract_excerpt":"Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07996","kind":"arxiv","version":2},"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/2203.07996/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":"2026-07-05T04:08:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DWoRYnIxuJVUyFEU602B9X0cR3WvH4jUgEW7Gy5rbCEpXQW4nJv0+F3emxl6LGcknBdwYNV3i+SU1/151gWZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:50:34.148004Z"},"content_sha256":"f35436257f9174c195fd36921e848c2dc5b2f619fb4eff5cd88480691f14f658","schema_version":"1.0","event_id":"sha256:f35436257f9174c195fd36921e848c2dc5b2f619fb4eff5cd88480691f14f658"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/bundle.json","state_url":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/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":"2026-07-07T07:50:34Z","links":{"resolver":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR","bundle":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/bundle.json","state":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HFUC5MYKO2LCRLCWTDS5T34TVR","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":"80c9c19439b6e735a4457db771d111a4a7f4b733a972419a6ba316fe13ceb809","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-24T15:12:17Z","title_canon_sha256":"912f4396d7c71458c26d1b2874298729317fd1d0eb2fce3f71bb784416743662"},"schema_version":"1.0","source":{"id":"2203.07996","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.07996","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"arxiv_version","alias_value":"2203.07996v2","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07996","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"pith_short_12","alias_value":"HFUC5MYKO2LC","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"pith_short_16","alias_value":"HFUC5MYKO2LCRLCW","created_at":"2026-07-05T04:08:42Z"},{"alias_kind":"pith_short_8","alias_value":"HFUC5MYK","created_at":"2026-07-05T04:08:42Z"}],"graph_snapshots":[{"event_id":"sha256:f35436257f9174c195fd36921e848c2dc5b2f619fb4eff5cd88480691f14f658","target":"graph","created_at":"2026-07-05T04:08:42Z","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/2203.07996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the m","authors_text":"Helong Zhou, Peiyu Chen, Xichen Pan, Xinbing Wang, Yichen Gong, Zhouhan Lin","cross_cats":["cs.AI","cs.CL","cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-24T15:12:17Z","title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07996","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:c80f9ae4f55783dfec7d87957ab5e39b8ab790292e80594531cc5cdf1af34bbc","target":"record","created_at":"2026-07-05T04:08:42Z","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":"80c9c19439b6e735a4457db771d111a4a7f4b733a972419a6ba316fe13ceb809","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-24T15:12:17Z","title_canon_sha256":"912f4396d7c71458c26d1b2874298729317fd1d0eb2fce3f71bb784416743662"},"schema_version":"1.0","source":{"id":"2203.07996","kind":"arxiv","version":2}},"canonical_sha256":"39682eb30a769628ac5698e5d9ef93ac787fe4d21bf4303b43152dac4a22aad7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39682eb30a769628ac5698e5d9ef93ac787fe4d21bf4303b43152dac4a22aad7","first_computed_at":"2026-07-05T04:08:42.985917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:42.985917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SR9GUYOqGkKYNajYGKy10kO5bprgNcBI6dqFo8nR5JPUYPShCpf8zZa4mzhkX/m/bVmRqNcMxh02vFW0PKZ4DA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:42.986268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.07996","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c80f9ae4f55783dfec7d87957ab5e39b8ab790292e80594531cc5cdf1af34bbc","sha256:f35436257f9174c195fd36921e848c2dc5b2f619fb4eff5cd88480691f14f658"],"state_sha256":"544058e0c04ebc9da23afcd41f1072fe88e464034d7c8ea10e94067dbdd9a88e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aGjKUwh8ZPGHJpTVSZ9GUNPxmaUhA9QtrAUvC+H/JqEzZhh8U7zhLXKBnE41I7BZKfWZlxHgg9eFTcdo4QWtCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:50:34.150718Z","bundle_sha256":"804aec51f141ca0abd8908d942b8935ff8a8c12eaafacd133bf9efce86f32c76"}}