{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4CTXGKVJBAM76O6IIUA2D5VYT6","short_pith_number":"pith:4CTXGKVJ","schema_version":"1.0","canonical_sha256":"e0a7732aa90819ff3bc84501a1f6b89f96c84fb1ab7ec2cfb1ac074c39d930d4","source":{"kind":"arxiv","id":"2202.07993","version":3},"attestation_state":"computed","paper":{"title":"Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Gomez-Villa, Andrew D. Bagdanov, Bart{\\l}omiej Twardowski, Joost Van De Weijer, Marco Buzzelli, Simone Zini","submitted_at":"2022-02-16T11:13:37Z","abstract_excerpt":"Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze how the color jitter traditionally used in data augmentation negatively impacts the quality of the color features in learned feature representations. To address this problem, we propose a more realistic, physics-based color data augmentation - which we call Planckian Jitter - that creates realistic variations in chrom"},"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":"2202.07993","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-16T11:13:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3fe4855c68591f80817d0325a6a2b5fdfe10b8a2897e3ee9989ed8d1c8b47f22","abstract_canon_sha256":"d972a14f15a1db87746b23fc5296dabeecc9efde55e285f68c1fd0d0ec245951"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:20.791609Z","signature_b64":"t2qJOgE+8PWWksurr1owDIQQa9wMvV1FQr+rlA7t1Rnmfhf/ulSAgjx54xmaOa1KT/8AwUR/cV40yxODhZU8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0a7732aa90819ff3bc84501a1f6b89f96c84fb1ab7ec2cfb1ac074c39d930d4","last_reissued_at":"2026-07-05T05:38:20.791126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:20.791126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Gomez-Villa, Andrew D. Bagdanov, Bart{\\l}omiej Twardowski, Joost Van De Weijer, Marco Buzzelli, Simone Zini","submitted_at":"2022-02-16T11:13:37Z","abstract_excerpt":"Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze how the color jitter traditionally used in data augmentation negatively impacts the quality of the color features in learned feature representations. To address this problem, we propose a more realistic, physics-based color data augmentation - which we call Planckian Jitter - that creates realistic variations in chrom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07993","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/2202.07993/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":"2202.07993","created_at":"2026-07-05T05:38:20.791183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07993v3","created_at":"2026-07-05T05:38:20.791183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07993","created_at":"2026-07-05T05:38:20.791183+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CTXGKVJBAM7","created_at":"2026-07-05T05:38:20.791183+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CTXGKVJBAM76O6I","created_at":"2026-07-05T05:38:20.791183+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CTXGKVJ","created_at":"2026-07-05T05:38:20.791183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.17489","citing_title":"LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6","json":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6.json","graph_json":"https://pith.science/api/pith-number/4CTXGKVJBAM76O6IIUA2D5VYT6/graph.json","events_json":"https://pith.science/api/pith-number/4CTXGKVJBAM76O6IIUA2D5VYT6/events.json","paper":"https://pith.science/paper/4CTXGKVJ"},"agent_actions":{"view_html":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6","download_json":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6.json","view_paper":"https://pith.science/paper/4CTXGKVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07993&json=true","fetch_graph":"https://pith.science/api/pith-number/4CTXGKVJBAM76O6IIUA2D5VYT6/graph.json","fetch_events":"https://pith.science/api/pith-number/4CTXGKVJBAM76O6IIUA2D5VYT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6/action/storage_attestation","attest_author":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6/action/author_attestation","sign_citation":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6/action/citation_signature","submit_replication":"https://pith.science/pith/4CTXGKVJBAM76O6IIUA2D5VYT6/action/replication_record"}},"created_at":"2026-07-05T05:38:20.791183+00:00","updated_at":"2026-07-05T05:38:20.791183+00:00"}