{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZKVC5EP4POD54KMXQYRAZEEUX5","short_pith_number":"pith:ZKVC5EP4","schema_version":"1.0","canonical_sha256":"caaa2e91fc7b87de299786220c9094bf5d3d32585fc99ba14b8cef9e358c991b","source":{"kind":"arxiv","id":"2112.00694","version":1},"attestation_state":"computed","paper":{"title":"Label-Free Model Evaluation with Semi-Structured Dataset Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongdong Li, Liang Zheng, Xiaoxiao Sun, Yunzhong Hou","submitted_at":"2021-12-01T18:15:58Z","abstract_excerpt":"Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on dataset representations, we estimate model performance for AutoEval with regression. On the one hand, image feature is a straightforward choice for such representations, but it hampers regression learning due to being unstructured (\\ie no specific meanings for component at certain location) and of large-scale. On the other hand, previous methods adopt simple structured representation"},"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":"2112.00694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T18:15:58Z","cross_cats_sorted":[],"title_canon_sha256":"12eb492f62441c2fab924bc43c64083379bbd647fa175174ece5b0d8ebf02cd6","abstract_canon_sha256":"873fe1c4b2251e728fab8da99ef0e339e3f01c07b157904c1cc950f9ee37fbea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:49.485156Z","signature_b64":"IiroDq4dcElDrvu9+ixaxVXvyzrYxNzH+DiYMVZc+5joq/JBBj2s2cQMGLZaJjTdIptmOVFh3cc7keptmTMQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caaa2e91fc7b87de299786220c9094bf5d3d32585fc99ba14b8cef9e358c991b","last_reissued_at":"2026-07-05T03:36:49.484750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:49.484750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-Free Model Evaluation with Semi-Structured Dataset Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongdong Li, Liang Zheng, Xiaoxiao Sun, Yunzhong Hou","submitted_at":"2021-12-01T18:15:58Z","abstract_excerpt":"Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on dataset representations, we estimate model performance for AutoEval with regression. On the one hand, image feature is a straightforward choice for such representations, but it hampers regression learning due to being unstructured (\\ie no specific meanings for component at certain location) and of large-scale. On the other hand, previous methods adopt simple structured representation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00694","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/2112.00694/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":"2112.00694","created_at":"2026-07-05T03:36:49.484809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00694v1","created_at":"2026-07-05T03:36:49.484809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00694","created_at":"2026-07-05T03:36:49.484809+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKVC5EP4POD5","created_at":"2026-07-05T03:36:49.484809+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKVC5EP4POD54KMX","created_at":"2026-07-05T03:36:49.484809+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKVC5EP4","created_at":"2026-07-05T03:36:49.484809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22356","citing_title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5","json":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5.json","graph_json":"https://pith.science/api/pith-number/ZKVC5EP4POD54KMXQYRAZEEUX5/graph.json","events_json":"https://pith.science/api/pith-number/ZKVC5EP4POD54KMXQYRAZEEUX5/events.json","paper":"https://pith.science/paper/ZKVC5EP4"},"agent_actions":{"view_html":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5","download_json":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5.json","view_paper":"https://pith.science/paper/ZKVC5EP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00694&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKVC5EP4POD54KMXQYRAZEEUX5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKVC5EP4POD54KMXQYRAZEEUX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5/action/storage_attestation","attest_author":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5/action/author_attestation","sign_citation":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5/action/citation_signature","submit_replication":"https://pith.science/pith/ZKVC5EP4POD54KMXQYRAZEEUX5/action/replication_record"}},"created_at":"2026-07-05T03:36:49.484809+00:00","updated_at":"2026-07-05T03:36:49.484809+00:00"}