{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EQBUFPRQF7DMLA3OAO3KVIGEVE","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":"52b5aa7bc550871447be632381f8521020c0ef7816058d958c1e15f407377d12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-23T18:07:13Z","title_canon_sha256":"d2ca4c776427ff04cd312090f27241da14044151689eab305e09f5eaef78029a"},"schema_version":"1.0","source":{"id":"2112.12750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.12750","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.12750v1","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12750","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"EQBUFPRQF7DM","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"EQBUFPRQF7DMLA3O","created_at":"2026-07-05T03:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"EQBUFPRQ","created_at":"2026-07-05T03:43:30Z"}],"graph_snapshots":[{"event_id":"sha256:decb81d167e9c6ade0e8728577c6372d48a7fcf8db621193382166f7ff831158","target":"graph","created_at":"2026-07-05T03:43:30Z","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/2112.12750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to learning with language supervision, demonstrates promising performance on a wide variety of benchmarks. In this work, we explore whether self-supervised learning can aid in the use of language supervision for visual representation learning. We introduce SLIP, a multi-task learning framework for combining self-supervised learning and CLIP pre-training. After pre-training with Vision Transformers, we thoroughly evaluate ","authors_text":"Alexander Kirillov, David Wagner, Norman Mu, Saining Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-23T18:07:13Z","title":"SLIP: Self-supervision meets Language-Image Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12750","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":"sha256:820ef8f20ac25fa99ba41b0b3a2306e237678ab370e1d8ee3bcbe2daef546a16","target":"record","created_at":"2026-07-05T03:43:30Z","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":"52b5aa7bc550871447be632381f8521020c0ef7816058d958c1e15f407377d12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-23T18:07:13Z","title_canon_sha256":"d2ca4c776427ff04cd312090f27241da14044151689eab305e09f5eaef78029a"},"schema_version":"1.0","source":{"id":"2112.12750","kind":"arxiv","version":1}},"canonical_sha256":"240342be302fc6c5836e03b6aaa0c4a9167971d618a4d7a64a90929be4fd9cea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"240342be302fc6c5836e03b6aaa0c4a9167971d618a4d7a64a90929be4fd9cea","first_computed_at":"2026-07-05T03:43:30.898759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:30.898759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xYCPlUV6PW/e9feZELpKQhV7mtKz3MRrwwPAL1AA4hR7m0VppERL3KYIyD4r7xZQZgFFod+ZmHw+yG/14ZRQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:30.899168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.12750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:820ef8f20ac25fa99ba41b0b3a2306e237678ab370e1d8ee3bcbe2daef546a16","sha256:decb81d167e9c6ade0e8728577c6372d48a7fcf8db621193382166f7ff831158"],"state_sha256":"c284de441eaa8efcb6720f48ab5d5fc9d40522dd986c12c463a53b07779c0254"}