{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KVQEBBELT7BWXSF7ATABT3N3Y4","short_pith_number":"pith:KVQEBBEL","schema_version":"1.0","canonical_sha256":"556040848b9fc36bc8bf04c019edbbc71e002701f64fba001c4c753c4cf62b4c","source":{"kind":"arxiv","id":"2603.04256","version":3},"attestation_state":"computed","paper":{"title":"A Hypertoroidal Covering for Perfect Color Equivariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christine Allen-Blanchette, Yaojun Li, Yulong Yang, Zhikun Xu","submitted_at":"2026-03-04T16:43:02Z","abstract_excerpt":"When the color distribution of input images changes at inference, the performance of conventional neural network architectures drops considerably. A few researchers have begun to incorporate prior knowledge of color geometry in neural network design. These color equivariant architectures have modeled hue variation with 2D rotations, and saturation and luminance transformations as 1D translations. While this approach improves neural network robustness to color variations in a number of contexts, we find that approximating saturation and luminance (interval valued quantities) as 1D translations "},"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":"2603.04256","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-04T16:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"d589df4efc51cad44dff2d1f65e21569712019f5519588faee6ca31ac1e396af","abstract_canon_sha256":"636bd5011dfc5dc05345363972d5aca7bb6af29b6fca6653e81bcfe56b3375ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:15.840498Z","signature_b64":"qGRV806CMTjCAYNneVYDPZVpErHDUY0dt4u6lCizQi2heehhLW0lIY5N5+KqI7ZVIq6hB3njWedjvn1v2Tl3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"556040848b9fc36bc8bf04c019edbbc71e002701f64fba001c4c753c4cf62b4c","last_reissued_at":"2026-06-02T01:03:15.840003Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:15.840003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hypertoroidal Covering for Perfect Color Equivariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christine Allen-Blanchette, Yaojun Li, Yulong Yang, Zhikun Xu","submitted_at":"2026-03-04T16:43:02Z","abstract_excerpt":"When the color distribution of input images changes at inference, the performance of conventional neural network architectures drops considerably. A few researchers have begun to incorporate prior knowledge of color geometry in neural network design. These color equivariant architectures have modeled hue variation with 2D rotations, and saturation and luminance transformations as 1D translations. While this approach improves neural network robustness to color variations in a number of contexts, we find that approximating saturation and luminance (interval valued quantities) as 1D translations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04256","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/2603.04256/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":"2603.04256","created_at":"2026-06-02T01:03:15.840064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.04256v3","created_at":"2026-06-02T01:03:15.840064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04256","created_at":"2026-06-02T01:03:15.840064+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVQEBBELT7BW","created_at":"2026-06-02T01:03:15.840064+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVQEBBELT7BWXSF7","created_at":"2026-06-02T01:03:15.840064+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVQEBBEL","created_at":"2026-06-02T01:03:15.840064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4","json":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4.json","graph_json":"https://pith.science/api/pith-number/KVQEBBELT7BWXSF7ATABT3N3Y4/graph.json","events_json":"https://pith.science/api/pith-number/KVQEBBELT7BWXSF7ATABT3N3Y4/events.json","paper":"https://pith.science/paper/KVQEBBEL"},"agent_actions":{"view_html":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4","download_json":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4.json","view_paper":"https://pith.science/paper/KVQEBBEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.04256&json=true","fetch_graph":"https://pith.science/api/pith-number/KVQEBBELT7BWXSF7ATABT3N3Y4/graph.json","fetch_events":"https://pith.science/api/pith-number/KVQEBBELT7BWXSF7ATABT3N3Y4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4/action/storage_attestation","attest_author":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4/action/author_attestation","sign_citation":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4/action/citation_signature","submit_replication":"https://pith.science/pith/KVQEBBELT7BWXSF7ATABT3N3Y4/action/replication_record"}},"created_at":"2026-06-02T01:03:15.840064+00:00","updated_at":"2026-06-02T01:03:15.840064+00:00"}