{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W6WPJJEB53KZPGTPFJVHXYO5XD","short_pith_number":"pith:W6WPJJEB","schema_version":"1.0","canonical_sha256":"b7acf4a481eed5979a6f2a6a7be1ddb8fa4e4f35754fd5c576790e8514789472","source":{"kind":"arxiv","id":"2306.12243","version":3},"attestation_state":"computed","paper":{"title":"Inter-Instance Similarity Modeling for Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengchao Shen, Dawei Liu, Hao Tang, Jianxin Wang, Zhe Qu","submitted_at":"2023-06-21T13:03:47Z","abstract_excerpt":"The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich inter-instance similarities among natural images, then leading to potential representation degeneration. In this paper, we propose a novel image mix method, PatchMix, for contrastive learning in Vision Transformer (ViT), to model inter-instance similarities among images. Following the nature of ViT, we randomly mix multiple images from mini-batch in patch level to construct mixed image patch sequences for ViT. Compared to the existi"},"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":"2306.12243","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-21T13:03:47Z","cross_cats_sorted":[],"title_canon_sha256":"e839a01cfa3e331f66f698c61d830ef3bfb7067b0752adfbb74b681293ee803b","abstract_canon_sha256":"ffa1eb73a9d8d93162f80f1fe2b547e4e9b4648ca5240f84886c6bfec689bd79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:03.007291Z","signature_b64":"0pcQuGBpe22p9io/xxLXx1LzyQkzbET2g4fVYvzoyr0uyBKBAnTyXFwziFkOig78aekW9hz3FhzYr6vyvjmxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7acf4a481eed5979a6f2a6a7be1ddb8fa4e4f35754fd5c576790e8514789472","last_reissued_at":"2026-07-05T06:26:03.006797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:03.006797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inter-Instance Similarity Modeling for Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengchao Shen, Dawei Liu, Hao Tang, Jianxin Wang, Zhe Qu","submitted_at":"2023-06-21T13:03:47Z","abstract_excerpt":"The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich inter-instance similarities among natural images, then leading to potential representation degeneration. In this paper, we propose a novel image mix method, PatchMix, for contrastive learning in Vision Transformer (ViT), to model inter-instance similarities among images. Following the nature of ViT, we randomly mix multiple images from mini-batch in patch level to construct mixed image patch sequences for ViT. Compared to the existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12243","kind":"arxiv","version":3},"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/2306.12243/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":"2306.12243","created_at":"2026-07-05T06:26:03.006853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12243v3","created_at":"2026-07-05T06:26:03.006853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12243","created_at":"2026-07-05T06:26:03.006853+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6WPJJEB53KZ","created_at":"2026-07-05T06:26:03.006853+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6WPJJEB53KZPGTP","created_at":"2026-07-05T06:26:03.006853+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6WPJJEB","created_at":"2026-07-05T06:26:03.006853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07364","citing_title":"Multiple Object Stitching for Unsupervised Representation Learning","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD","json":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD.json","graph_json":"https://pith.science/api/pith-number/W6WPJJEB53KZPGTPFJVHXYO5XD/graph.json","events_json":"https://pith.science/api/pith-number/W6WPJJEB53KZPGTPFJVHXYO5XD/events.json","paper":"https://pith.science/paper/W6WPJJEB"},"agent_actions":{"view_html":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD","download_json":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD.json","view_paper":"https://pith.science/paper/W6WPJJEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12243&json=true","fetch_graph":"https://pith.science/api/pith-number/W6WPJJEB53KZPGTPFJVHXYO5XD/graph.json","fetch_events":"https://pith.science/api/pith-number/W6WPJJEB53KZPGTPFJVHXYO5XD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD/action/storage_attestation","attest_author":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD/action/author_attestation","sign_citation":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD/action/citation_signature","submit_replication":"https://pith.science/pith/W6WPJJEB53KZPGTPFJVHXYO5XD/action/replication_record"}},"created_at":"2026-07-05T06:26:03.006853+00:00","updated_at":"2026-07-05T06:26:03.006853+00:00"}