{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NVN5DT6X4ANWHSHE2HWBOJQLK3","short_pith_number":"pith:NVN5DT6X","schema_version":"1.0","canonical_sha256":"6d5bd1cfd7e01b63c8e4d1ec17260b56d860829aa7a56f7d23b7b2c986f9690b","source":{"kind":"arxiv","id":"2012.11552","version":2},"attestation_state":"computed","paper":{"title":"OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Gilles Puy, Matthieu Cord, Nikos Komodakis, Patrick P\\'erez, Spyros Gidaris","submitted_at":"2020-12-21T18:31:21Z","abstract_excerpt":"Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a representation invariant under different types of perturbations, especially via contrastive-based instance discrimination training. Although effective visual representations should indeed exhibit such invariances, there are other important characteristics, such as encoding contextual reasoning skills, for which alternative reconstruction-based approaches might be better suited.\n  With this in mind, we propose a teach"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2012.11552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-21T18:31:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c0ed0a1f5b17f76337dc1aba30a081c2167bac25a53faaac66adf6de02236ffc","abstract_canon_sha256":"a961c6b44d973213ad47ca7a9dc84724d60e676cf29774b770d5a9f0a3693c94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:58.172984Z","signature_b64":"sGv62G+V/gBHOVzN4IunAcXUpMfHvW5DB7pBw+xOUo+09u8ChtY1AmP3Z6c9OxssGaj5RGt5zsndYQtxjCSvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5bd1cfd7e01b63c8e4d1ec17260b56d860829aa7a56f7d23b7b2c986f9690b","last_reissued_at":"2026-07-05T03:26:58.172442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:58.172442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Gilles Puy, Matthieu Cord, Nikos Komodakis, Patrick P\\'erez, Spyros Gidaris","submitted_at":"2020-12-21T18:31:21Z","abstract_excerpt":"Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a representation invariant under different types of perturbations, especially via contrastive-based instance discrimination training. Although effective visual representations should indeed exhibit such invariances, there are other important characteristics, such as encoding contextual reasoning skills, for which alternative reconstruction-based approaches might be better suited.\n  With this in mind, we propose a teach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11552","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/2012.11552/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2012.11552","created_at":"2026-07-05T03:26:58.172519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11552v2","created_at":"2026-07-05T03:26:58.172519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11552","created_at":"2026-07-05T03:26:58.172519+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVN5DT6X4ANW","created_at":"2026-07-05T03:26:58.172519+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVN5DT6X4ANWHSHE","created_at":"2026-07-05T03:26:58.172519+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVN5DT6X","created_at":"2026-07-05T03:26:58.172519+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2104.14294","citing_title":"Emerging Properties in Self-Supervised Vision Transformers","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16588","citing_title":"Vision Transformers Need Registers","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3","json":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3.json","graph_json":"https://pith.science/api/pith-number/NVN5DT6X4ANWHSHE2HWBOJQLK3/graph.json","events_json":"https://pith.science/api/pith-number/NVN5DT6X4ANWHSHE2HWBOJQLK3/events.json","paper":"https://pith.science/paper/NVN5DT6X"},"agent_actions":{"view_html":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3","download_json":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3.json","view_paper":"https://pith.science/paper/NVN5DT6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11552&json=true","fetch_graph":"https://pith.science/api/pith-number/NVN5DT6X4ANWHSHE2HWBOJQLK3/graph.json","fetch_events":"https://pith.science/api/pith-number/NVN5DT6X4ANWHSHE2HWBOJQLK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3/action/storage_attestation","attest_author":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3/action/author_attestation","sign_citation":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3/action/citation_signature","submit_replication":"https://pith.science/pith/NVN5DT6X4ANWHSHE2HWBOJQLK3/action/replication_record"}},"created_at":"2026-07-05T03:26:58.172519+00:00","updated_at":"2026-07-05T03:26:58.172519+00:00"}