{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Q4NLV5SUQ6ZDHW4HCBJBYTTYSL","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":"48fc637f07b883a066077eea3c9be14495ccd100d3cf160761d0d661631478a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-29T17:50:23Z","title_canon_sha256":"d50d7e621ab0b4a4bd065172800f0eab8e323ea77a522eca63677b8f081d8ac7"},"schema_version":"1.0","source":{"id":"2006.16228","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.16228","created_at":"2026-07-05T01:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2006.16228v2","created_at":"2026-07-05T01:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16228","created_at":"2026-07-05T01:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"Q4NLV5SUQ6ZD","created_at":"2026-07-05T01:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"Q4NLV5SUQ6ZDHW4H","created_at":"2026-07-05T01:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"Q4NLV5SU","created_at":"2026-07-05T01:47:44Z"}],"graph_snapshots":[{"event_id":"sha256:5cc855d9e29491730de25f8eb4df75623e07e067515405ce47a442a740bcc20a","target":"graph","created_at":"2026-07-05T01:47:44Z","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/2006.16228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. To this end, we introduce the notion of a multimodal versatile network -- a network that can ingest multiple modalities and whose representations enable downstream tasks in multiple modalities. In particular, we explore how best to combine the modalities, such that fine-grained representations of the visual and audio modalities can be maintained, whilst also integrating text into a comm","authors_text":"Adri\\`a Recasens, Andrew Zisserman, Jason Ramapuram, Jean-Baptiste Alayrac, Jeffrey De Fauw, Lucas Smaira, Relja Arandjelovi\\'c, Rosalia Schneider, Sander Dieleman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-29T17:50:23Z","title":"Self-Supervised MultiModal Versatile Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16228","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":"sha256:81c9e80884a322f7c41523d1698d1cda7bc400e941f1569d3c460d2e993019e2","target":"record","created_at":"2026-07-05T01:47:44Z","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":"48fc637f07b883a066077eea3c9be14495ccd100d3cf160761d0d661631478a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-29T17:50:23Z","title_canon_sha256":"d50d7e621ab0b4a4bd065172800f0eab8e323ea77a522eca63677b8f081d8ac7"},"schema_version":"1.0","source":{"id":"2006.16228","kind":"arxiv","version":2}},"canonical_sha256":"871abaf65487b233db8710521c4e7892fe8210f7532a88fce08a51be92626b40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"871abaf65487b233db8710521c4e7892fe8210f7532a88fce08a51be92626b40","first_computed_at":"2026-07-05T01:47:44.472965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:44.472965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HuZwGjDB68BkQKr0fHH58a3BkUvRpr8Nk4IM7cTX+8IYDadF8C9PsQwosxhJbAvHXxPVdhz+tVWeDCV5yC3lDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:44.473363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.16228","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81c9e80884a322f7c41523d1698d1cda7bc400e941f1569d3c460d2e993019e2","sha256:5cc855d9e29491730de25f8eb4df75623e07e067515405ce47a442a740bcc20a"],"state_sha256":"3ae8e800f73d23351700e4254087fb842392e5cfcc5c47e042584047c1024802"}