{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GTCTZUH6AIJWMG2TSM7IEW23M5","short_pith_number":"pith:GTCTZUH6","schema_version":"1.0","canonical_sha256":"34c53cd0fe0213661b53933e825b5b675b4d69aa9e9ff5d9e6255eb76dc18021","source":{"kind":"arxiv","id":"2312.10747","version":1},"attestation_state":"computed","paper":{"title":"CEIR: Concept-based Explainable Image Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Liuzhuozheng Li, Shuhong Liu, Yan Cui, Zhiyuan Yuan","submitted_at":"2023-12-17T15:37:41Z","abstract_excerpt":"In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the inherently high-dimensional nature, improves the difficulty for the interpretation of learned representations. Consequently, indirect evaluations become the popular metric for evaluating the quality of these features, leading to a biased validation of the learned representation rationale. To address these challenges, we introduce a novel approach termed Concept"},"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":"2312.10747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T15:37:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ea9144e30282b72bf24e5bdf39d88e3a7c84c4a9219dc27b35a1e1ece97329c4","abstract_canon_sha256":"ec2846381b5aa2c7d3495bac4c964450cfb85e571f8bef91150ecb37290f2c8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:11.727143Z","signature_b64":"LZTbee/DTUvvSAABqE/ZwXuKxK8a43U+es1bfE2YoJvlPQr07hDpa2+0Yvx8LvRo0hGPoBghoRP1msrI4Kk7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c53cd0fe0213661b53933e825b5b675b4d69aa9e9ff5d9e6255eb76dc18021","last_reissued_at":"2026-07-05T07:25:11.726603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:11.726603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CEIR: Concept-based Explainable Image Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Liuzhuozheng Li, Shuhong Liu, Yan Cui, Zhiyuan Yuan","submitted_at":"2023-12-17T15:37:41Z","abstract_excerpt":"In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the inherently high-dimensional nature, improves the difficulty for the interpretation of learned representations. Consequently, indirect evaluations become the popular metric for evaluating the quality of these features, leading to a biased validation of the learned representation rationale. To address these challenges, we introduce a novel approach termed Concept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10747","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/2312.10747/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":"2312.10747","created_at":"2026-07-05T07:25:11.726665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10747v1","created_at":"2026-07-05T07:25:11.726665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10747","created_at":"2026-07-05T07:25:11.726665+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTCTZUH6AIJW","created_at":"2026-07-05T07:25:11.726665+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTCTZUH6AIJWMG2T","created_at":"2026-07-05T07:25:11.726665+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTCTZUH6","created_at":"2026-07-05T07:25:11.726665+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/GTCTZUH6AIJWMG2TSM7IEW23M5","json":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5.json","graph_json":"https://pith.science/api/pith-number/GTCTZUH6AIJWMG2TSM7IEW23M5/graph.json","events_json":"https://pith.science/api/pith-number/GTCTZUH6AIJWMG2TSM7IEW23M5/events.json","paper":"https://pith.science/paper/GTCTZUH6"},"agent_actions":{"view_html":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5","download_json":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5.json","view_paper":"https://pith.science/paper/GTCTZUH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10747&json=true","fetch_graph":"https://pith.science/api/pith-number/GTCTZUH6AIJWMG2TSM7IEW23M5/graph.json","fetch_events":"https://pith.science/api/pith-number/GTCTZUH6AIJWMG2TSM7IEW23M5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5/action/storage_attestation","attest_author":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5/action/author_attestation","sign_citation":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5/action/citation_signature","submit_replication":"https://pith.science/pith/GTCTZUH6AIJWMG2TSM7IEW23M5/action/replication_record"}},"created_at":"2026-07-05T07:25:11.726665+00:00","updated_at":"2026-07-05T07:25:11.726665+00:00"}