{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YE32G422AUK2AF3IFYR52PUCJE","short_pith_number":"pith:YE32G422","schema_version":"1.0","canonical_sha256":"c137a3735a0515a017682e23dd3e82491c4f899371b35f6a021ae5f2e3ecde5b","source":{"kind":"arxiv","id":"2608.09052","version":1},"attestation_state":"computed","paper":{"title":"Triple Expert Learning from Noisy Labels for Semi-Supervised Vision Foundation Model Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Hongyang He, Xuanyu Liu, Yundi Hong, Zheng Fang","submitted_at":"2026-08-10T03:00:17Z","abstract_excerpt":"Semi-supervised adaptation of vision foundation models (VFMs) commonly freezes the pretrained backbone and updates lightweight modules such as LoRA. However, pseudo-labels have mixed reliability, and a single LoRA adapter must absorb reliable, ambiguous, and noisy gradients in the same low-rank space. This can make VFM adaptation sensitive to pseudo-label noise. We propose \\textbf{TriNoL}, a \\textbf{Tri}ple-expert learning framework from \\textbf{No}isy \\textbf{L}abels for semi-supervised VFM adaptation. TriNoL routes unlabeled samples into three confidence regions and assigns them to three LoR"},"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":"2608.09052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T03:00:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df8b425876c85d35fa10b6fa20bad5a09ea9f3f01f34a812c846ee7e9c3349e8","abstract_canon_sha256":"7299fb96b1928fd7e5a8570871a9c9579499f39737d5b4099cb75c1541ee3b46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:21:41.538338Z","signature_b64":"Zw/NiIerYvFbU5+/VBkvkAixWjP0JQCPE8oS8TvaaLAgFW0AaEsqrToF4tT2wzW//DqXPPB3n3KPAjKSDy2ODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c137a3735a0515a017682e23dd3e82491c4f899371b35f6a021ae5f2e3ecde5b","last_reissued_at":"2026-08-11T02:21:41.536612Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:21:41.536612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triple Expert Learning from Noisy Labels for Semi-Supervised Vision Foundation Model Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Hongyang He, Xuanyu Liu, Yundi Hong, Zheng Fang","submitted_at":"2026-08-10T03:00:17Z","abstract_excerpt":"Semi-supervised adaptation of vision foundation models (VFMs) commonly freezes the pretrained backbone and updates lightweight modules such as LoRA. However, pseudo-labels have mixed reliability, and a single LoRA adapter must absorb reliable, ambiguous, and noisy gradients in the same low-rank space. This can make VFM adaptation sensitive to pseudo-label noise. We propose \\textbf{TriNoL}, a \\textbf{Tri}ple-expert learning framework from \\textbf{No}isy \\textbf{L}abels for semi-supervised VFM adaptation. TriNoL routes unlabeled samples into three confidence regions and assigns them to three LoR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09052","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/2608.09052/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":"2608.09052","created_at":"2026-08-11T02:21:41.537325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09052v1","created_at":"2026-08-11T02:21:41.537325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09052","created_at":"2026-08-11T02:21:41.537325+00:00"},{"alias_kind":"pith_short_12","alias_value":"YE32G422AUK2","created_at":"2026-08-11T02:21:41.537325+00:00"},{"alias_kind":"pith_short_16","alias_value":"YE32G422AUK2AF3I","created_at":"2026-08-11T02:21:41.537325+00:00"},{"alias_kind":"pith_short_8","alias_value":"YE32G422","created_at":"2026-08-11T02:21:41.537325+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/YE32G422AUK2AF3IFYR52PUCJE","json":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE.json","graph_json":"https://pith.science/api/pith-number/YE32G422AUK2AF3IFYR52PUCJE/graph.json","events_json":"https://pith.science/api/pith-number/YE32G422AUK2AF3IFYR52PUCJE/events.json","paper":"https://pith.science/paper/YE32G422"},"agent_actions":{"view_html":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE","download_json":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE.json","view_paper":"https://pith.science/paper/YE32G422","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09052&json=true","fetch_graph":"https://pith.science/api/pith-number/YE32G422AUK2AF3IFYR52PUCJE/graph.json","fetch_events":"https://pith.science/api/pith-number/YE32G422AUK2AF3IFYR52PUCJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE/action/storage_attestation","attest_author":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE/action/author_attestation","sign_citation":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE/action/citation_signature","submit_replication":"https://pith.science/pith/YE32G422AUK2AF3IFYR52PUCJE/action/replication_record"}},"created_at":"2026-08-11T02:21:41.537325+00:00","updated_at":"2026-08-11T02:21:41.537325+00:00"}