{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IMU3AOGM2DKU2RY7LIYHX5BFZD","short_pith_number":"pith:IMU3AOGM","canonical_record":{"source":{"id":"2605.23254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T05:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"d894c3ccbba9fb1197434d1a867ea3317f3c46fca2f893eb4426b8682950684c","abstract_canon_sha256":"817e548a4b688e20ccdd85feb2495065079d92b8f19c82e891262a31998cfa77"},"schema_version":"1.0"},"canonical_sha256":"4329b038ccd0d54d471f5a307bf425c8d404ea96b7c93414703395cc196450a2","source":{"kind":"arxiv","id":"2605.23254","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23254","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23254v1","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23254","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"IMU3AOGM2DKU","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"IMU3AOGM2DKU2RY7","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"IMU3AOGM","created_at":"2026-05-25T02:01:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IMU3AOGM2DKU2RY7LIYHX5BFZD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T05:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"d894c3ccbba9fb1197434d1a867ea3317f3c46fca2f893eb4426b8682950684c","abstract_canon_sha256":"817e548a4b688e20ccdd85feb2495065079d92b8f19c82e891262a31998cfa77"},"schema_version":"1.0"},"canonical_sha256":"4329b038ccd0d54d471f5a307bf425c8d404ea96b7c93414703395cc196450a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:45.852678Z","signature_b64":"c+CiCJDvRuow/zOBdcatLRUkmX2Zs2WZGAU9JrcKvr8ic5vov2ZSbUrBy+5ys5cZycYSMZZnVzovOJ6niuclBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4329b038ccd0d54d471f5a307bf425c8d404ea96b7c93414703395cc196450a2","last_reissued_at":"2026-05-25T02:01:45.852203Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:45.852203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23254","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AAlUoX1TKgmjYPf91+3bWK+jnGTmjd0WR17SHviimzr/jb0TrDlIWUCTVEnusNjUsi3klNlN4Is0t8vRuT00AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:48:17.057908Z"},"content_sha256":"79db0db571aae0e15758b29086dd4d07e7b248408631338927b4fb12e20887c6","schema_version":"1.0","event_id":"sha256:79db0db571aae0e15758b29086dd4d07e7b248408631338927b4fb12e20887c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IMU3AOGM2DKU2RY7LIYHX5BFZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiquan Ling, Hui Huang, Lihao Chen, Mengke Li, Yang Lu, Yiqun Zhang","submitted_at":"2026-05-22T05:58:44Z","abstract_excerpt":"Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing methods partially address these issues but typically ignore the non-uniform impact of label noise across classes, resulting in ineffective correction for tail classes and over-regularization for head classes. To address this issue, we propose Class-Adaptive Rectification with Experts (CARE), a parameter-efficient framework that leverages three complementary supervision sources from vision-language models (VLM): observed noisy labels, VLM text embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23254","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/2605.23254/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNmLqyxNrcMeDOz6a6f6qfp58nrLC4yyaGeCFgjQJZ1DTwaHNokCfX3LfGou8oHZjWKlzEKCXBqTdylvZHMmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:48:17.058681Z"},"content_sha256":"86356ab0b3d61b5ecd9776585fd83641c42b4c2bb42731b98ba9cbc8680ce998","schema_version":"1.0","event_id":"sha256:86356ab0b3d61b5ecd9776585fd83641c42b4c2bb42731b98ba9cbc8680ce998"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMU3AOGM2DKU2RY7LIYHX5BFZD/bundle.json","state_url":"https://pith.science/pith/IMU3AOGM2DKU2RY7LIYHX5BFZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMU3AOGM2DKU2RY7LIYHX5BFZD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T19:48:17Z","links":{"resolver":"https://pith.science/pith/IMU3AOGM2DKU2RY7LIYHX5BFZD","bundle":"https://pith.science/pith/IMU3AOGM2DKU2RY7LIYHX5BFZD/bundle.json","state":"https://pith.science/pith/IMU3AOGM2DKU2RY7LIYHX5BFZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMU3AOGM2DKU2RY7LIYHX5BFZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IMU3AOGM2DKU2RY7LIYHX5BFZD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"817e548a4b688e20ccdd85feb2495065079d92b8f19c82e891262a31998cfa77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T05:58:44Z","title_canon_sha256":"d894c3ccbba9fb1197434d1a867ea3317f3c46fca2f893eb4426b8682950684c"},"schema_version":"1.0","source":{"id":"2605.23254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23254","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23254v1","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23254","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"IMU3AOGM2DKU","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"IMU3AOGM2DKU2RY7","created_at":"2026-05-25T02:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"IMU3AOGM","created_at":"2026-05-25T02:01:45Z"}],"graph_snapshots":[{"event_id":"sha256:86356ab0b3d61b5ecd9776585fd83641c42b4c2bb42731b98ba9cbc8680ce998","target":"graph","created_at":"2026-05-25T02:01:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.23254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing methods partially address these issues but typically ignore the non-uniform impact of label noise across classes, resulting in ineffective correction for tail classes and over-regularization for head classes. To address this issue, we propose Class-Adaptive Rectification with Experts (CARE), a parameter-efficient framework that leverages three complementary supervision sources from vision-language models (VLM): observed noisy labels, VLM text embeddi","authors_text":"Haiquan Ling, Hui Huang, Lihao Chen, Mengke Li, Yang Lu, Yiqun Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T05:58:44Z","title":"CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23254","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79db0db571aae0e15758b29086dd4d07e7b248408631338927b4fb12e20887c6","target":"record","created_at":"2026-05-25T02:01:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"817e548a4b688e20ccdd85feb2495065079d92b8f19c82e891262a31998cfa77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T05:58:44Z","title_canon_sha256":"d894c3ccbba9fb1197434d1a867ea3317f3c46fca2f893eb4426b8682950684c"},"schema_version":"1.0","source":{"id":"2605.23254","kind":"arxiv","version":1}},"canonical_sha256":"4329b038ccd0d54d471f5a307bf425c8d404ea96b7c93414703395cc196450a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4329b038ccd0d54d471f5a307bf425c8d404ea96b7c93414703395cc196450a2","first_computed_at":"2026-05-25T02:01:45.852203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:45.852203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c+CiCJDvRuow/zOBdcatLRUkmX2Zs2WZGAU9JrcKvr8ic5vov2ZSbUrBy+5ys5cZycYSMZZnVzovOJ6niuclBA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:45.852678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79db0db571aae0e15758b29086dd4d07e7b248408631338927b4fb12e20887c6","sha256:86356ab0b3d61b5ecd9776585fd83641c42b4c2bb42731b98ba9cbc8680ce998"],"state_sha256":"00226f6e3d1f3e25cfb4a975329ddd1b0a7b3bc32136c850fe8fe939ffbefce9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9bOYG06cdWWsEkPUcSHdGm9+CvcBXyeI/7zhCwPN3fG/tb8P6AqY6ZG2Q0z4ldfMkulNoI6YQWljCJmw6gzDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:48:17.062572Z","bundle_sha256":"aa9a8cfc42933464543a5ae79b71816d1f73da46b2f8195452de778e2ebee680"}}