{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WAQTKTNCHQQIJAURHGQIRE2HPY","short_pith_number":"pith:WAQTKTNC","schema_version":"1.0","canonical_sha256":"b021354da23c2084829139a08893477e3f0eb5973ccabd4ae9a0be4426abc8e2","source":{"kind":"arxiv","id":"2208.06412","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Learning for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunal Rathore, Rishab Balasubramanian","submitted_at":"2022-08-12T02:02:23Z","abstract_excerpt":"Contrastive learning is commonly used as a method of self-supervised learning with the \"anchor\" and \"positive\" being two random augmentations of a given input image, and the \"negative\" is the set of all other images. However, the requirement of large batch sizes and memory banks has made it difficult and slow to train. This has motivated the rise of Supervised Contrasative approaches that overcome these problems by using annotated data. We look to further improve supervised contrastive learning by ranking classes based on their similarity, and observe the impact of human bias (in the form of r"},"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":"2208.06412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T02:02:23Z","cross_cats_sorted":[],"title_canon_sha256":"4237e0f1c520fa53345306cd1ee7384fc15e5e88de003ca1ace07bcec34625c1","abstract_canon_sha256":"736a91e44ddbcff9c55a69e5fbc91bd3c008b67ad1ad7433c8280f5552855fa5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:16.463845Z","signature_b64":"pnqRZ4H/Z9hfMvKe72epiPT7BkeomvgCGvrBWGcxMsipcncgIBJhyy9yJo84siidFi1JYltrr+GsXBGo8J66Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b021354da23c2084829139a08893477e3f0eb5973ccabd4ae9a0be4426abc8e2","last_reissued_at":"2026-07-05T04:48:16.463472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:16.463472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Learning for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunal Rathore, Rishab Balasubramanian","submitted_at":"2022-08-12T02:02:23Z","abstract_excerpt":"Contrastive learning is commonly used as a method of self-supervised learning with the \"anchor\" and \"positive\" being two random augmentations of a given input image, and the \"negative\" is the set of all other images. However, the requirement of large batch sizes and memory banks has made it difficult and slow to train. This has motivated the rise of Supervised Contrasative approaches that overcome these problems by using annotated data. We look to further improve supervised contrastive learning by ranking classes based on their similarity, and observe the impact of human bias (in the form of r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06412","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/2208.06412/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":"2208.06412","created_at":"2026-07-05T04:48:16.463528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.06412v1","created_at":"2026-07-05T04:48:16.463528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06412","created_at":"2026-07-05T04:48:16.463528+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAQTKTNCHQQI","created_at":"2026-07-05T04:48:16.463528+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAQTKTNCHQQIJAUR","created_at":"2026-07-05T04:48:16.463528+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAQTKTNC","created_at":"2026-07-05T04:48:16.463528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04696","citing_title":"Achieving Precise and Reliable Locomotion with Differentiable Simulation-Based System Identification","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY","json":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY.json","graph_json":"https://pith.science/api/pith-number/WAQTKTNCHQQIJAURHGQIRE2HPY/graph.json","events_json":"https://pith.science/api/pith-number/WAQTKTNCHQQIJAURHGQIRE2HPY/events.json","paper":"https://pith.science/paper/WAQTKTNC"},"agent_actions":{"view_html":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY","download_json":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY.json","view_paper":"https://pith.science/paper/WAQTKTNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.06412&json=true","fetch_graph":"https://pith.science/api/pith-number/WAQTKTNCHQQIJAURHGQIRE2HPY/graph.json","fetch_events":"https://pith.science/api/pith-number/WAQTKTNCHQQIJAURHGQIRE2HPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY/action/storage_attestation","attest_author":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY/action/author_attestation","sign_citation":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY/action/citation_signature","submit_replication":"https://pith.science/pith/WAQTKTNCHQQIJAURHGQIRE2HPY/action/replication_record"}},"created_at":"2026-07-05T04:48:16.463528+00:00","updated_at":"2026-07-05T04:48:16.463528+00:00"}