{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GPVMHOWQ4JGBRK3C3GJNUHR637","short_pith_number":"pith:GPVMHOWQ","schema_version":"1.0","canonical_sha256":"33eac3bad0e24c18ab62d992da1e3edfff5fc4dd069d356a8f7ec06176d010f7","source":{"kind":"arxiv","id":"2104.13712","version":1},"attestation_state":"computed","paper":{"title":"A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Louis-Philippe Morency, Ruslan Salakhutdinov, Shaojie Bai, Yao-Hung Hubert Tsai","submitted_at":"2021-04-28T11:36:09Z","abstract_excerpt":"In this report, we relate the algorithmic design of Barlow Twins' method to the Hilbert-Schmidt Independence Criterion (HSIC), thus establishing it as a contrastive learning approach that is free of negative samples. Through this perspective, we argue that Barlow Twins (and thus the class of negative-sample-free contrastive learning methods) suggests a possibility to bridge the two major families of self-supervised learning philosophies: non-contrastive and contrastive approaches. In particular, Barlow twins exemplified how we could combine the best practices of both worlds: avoiding the need "},"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":"2104.13712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-28T11:36:09Z","cross_cats_sorted":[],"title_canon_sha256":"dad0ba8f9c29ed7abb8f88741143b208c54ee1577ec46ef879b33f7526122639","abstract_canon_sha256":"4b014545e14a00697f4d2cf294f3f69235f737286d789bff1ce044e1350194f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:57.519478Z","signature_b64":"8/LTL4DWaL+tmS1NfW80dxA1zrDoEvBJKNaG/vdmOvPbsOLo8Hgm2go6dEwFs6UCzRNsbz33wr6XnJt+hYZcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33eac3bad0e24c18ab62d992da1e3edfff5fc4dd069d356a8f7ec06176d010f7","last_reissued_at":"2026-07-05T02:35:57.518952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:57.518952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Louis-Philippe Morency, Ruslan Salakhutdinov, Shaojie Bai, Yao-Hung Hubert Tsai","submitted_at":"2021-04-28T11:36:09Z","abstract_excerpt":"In this report, we relate the algorithmic design of Barlow Twins' method to the Hilbert-Schmidt Independence Criterion (HSIC), thus establishing it as a contrastive learning approach that is free of negative samples. Through this perspective, we argue that Barlow Twins (and thus the class of negative-sample-free contrastive learning methods) suggests a possibility to bridge the two major families of self-supervised learning philosophies: non-contrastive and contrastive approaches. In particular, Barlow twins exemplified how we could combine the best practices of both worlds: avoiding the need "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13712","kind":"arxiv","version":1},"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/2104.13712/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":"2104.13712","created_at":"2026-07-05T02:35:57.519015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13712v1","created_at":"2026-07-05T02:35:57.519015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13712","created_at":"2026-07-05T02:35:57.519015+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPVMHOWQ4JGB","created_at":"2026-07-05T02:35:57.519015+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPVMHOWQ4JGBRK3C","created_at":"2026-07-05T02:35:57.519015+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPVMHOWQ","created_at":"2026-07-05T02:35:57.519015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":163,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637","json":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637.json","graph_json":"https://pith.science/api/pith-number/GPVMHOWQ4JGBRK3C3GJNUHR637/graph.json","events_json":"https://pith.science/api/pith-number/GPVMHOWQ4JGBRK3C3GJNUHR637/events.json","paper":"https://pith.science/paper/GPVMHOWQ"},"agent_actions":{"view_html":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637","download_json":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637.json","view_paper":"https://pith.science/paper/GPVMHOWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13712&json=true","fetch_graph":"https://pith.science/api/pith-number/GPVMHOWQ4JGBRK3C3GJNUHR637/graph.json","fetch_events":"https://pith.science/api/pith-number/GPVMHOWQ4JGBRK3C3GJNUHR637/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637/action/storage_attestation","attest_author":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637/action/author_attestation","sign_citation":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637/action/citation_signature","submit_replication":"https://pith.science/pith/GPVMHOWQ4JGBRK3C3GJNUHR637/action/replication_record"}},"created_at":"2026-07-05T02:35:57.519015+00:00","updated_at":"2026-07-05T02:35:57.519015+00:00"}