{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KGO5X5TIAS7PFY25TKMFWZPJU2","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":"0c49dc2c088fa0af5c2db5a45354779b8fc099180cf9b1a9b1d8df5fa30cc71c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T22:52:11Z","title_canon_sha256":"215b9661dab5df68adca48230fad995fb42d8a78c1ffbde1c6d3fbfc1939235d"},"schema_version":"1.0","source":{"id":"2202.03555","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03555","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03555v3","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03555","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"KGO5X5TIAS7P","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"KGO5X5TIAS7PFY25","created_at":"2026-07-05T05:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"KGO5X5TI","created_at":"2026-07-05T05:10:36Z"}],"graph_snapshots":[{"event_id":"sha256:df8055976a67e75f9961160597dea37443991dc09a386894b5e522e6fc327b02","target":"graph","created_at":"2026-07-05T05:10:36Z","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/2202.03555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised learning, we present data2vec, a framework that uses the same learning method for either speech, NLP or computer vision. The core idea is to predict latent representations of the full input data based on a masked view of the input in a self-distillation setup using a standard Transformer architecture. Instead of predicting modality-specific targets such as wor","authors_text":"Alexei Baevski, Arun Babu, Jiatao Gu, Michael Auli, Qiantong Xu, Wei-Ning Hsu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T22:52:11Z","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03555","kind":"arxiv","version":3},"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":"sha256:0cb944aef124e380cb3b3fea598b4143aad9e0e14a499f8e179266a36a56772b","target":"record","created_at":"2026-07-05T05:10:36Z","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":"0c49dc2c088fa0af5c2db5a45354779b8fc099180cf9b1a9b1d8df5fa30cc71c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T22:52:11Z","title_canon_sha256":"215b9661dab5df68adca48230fad995fb42d8a78c1ffbde1c6d3fbfc1939235d"},"schema_version":"1.0","source":{"id":"2202.03555","kind":"arxiv","version":3}},"canonical_sha256":"519ddbf66804bef2e35d9a985b65e9a696ee9c1f1897a53ac6a3fc5e37d165bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"519ddbf66804bef2e35d9a985b65e9a696ee9c1f1897a53ac6a3fc5e37d165bb","first_computed_at":"2026-07-05T05:10:36.502894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:36.502894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NGPDIzWSypQtu/3V0Uz+gjSTB1OuRuG/AXDOPEr2TxadF/3eM92F09KfiLbIBi72mFP+lJzysXMyokyKpzSMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:36.503400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03555","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cb944aef124e380cb3b3fea598b4143aad9e0e14a499f8e179266a36a56772b","sha256:df8055976a67e75f9961160597dea37443991dc09a386894b5e522e6fc327b02"],"state_sha256":"6e784ceb4d1fc4381e908eac12c11d1e2b08bf8d8c69df374614254d71f5c573"}