{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RMHGM2U2TVJUSB5X66IOB2QJNP","short_pith_number":"pith:RMHGM2U2","schema_version":"1.0","canonical_sha256":"8b0e666a9a9d534907b7f790e0ea096bc777348344802ff83ff16f9f946d43b4","source":{"kind":"arxiv","id":"2507.19847","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Wenjie Zhu, Wenjun Zeng, Xin Jin, Yabin Zhang","submitted_at":"2025-07-26T07:44:04Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for building reliable machine learning models. Although negative prompt tuning has enhanced the OOD detection capabilities of vision-language models, these tuned models often suffer from reduced generalization performance on unseen classes and styles. To address this challenge, we propose a novel method called Knowledge Regularized Negative Feature Tuning (KR-NFT), which integrates an innovative adaptation architecture termed Negative Feature Tuning (NFT) and a corresponding knowledge-regularization (KR) optimization strategy. Specifically, NFT ap"},"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":"2507.19847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T07:44:04Z","cross_cats_sorted":[],"title_canon_sha256":"c8493efd261198e3db02381308cdbe5151433ba7e8ef0be088ae8cf053c28699","abstract_canon_sha256":"16eae544a5b57f3d68b1f54d993929e2a911feec97a20776c2e307931b08fa37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:53.087845Z","signature_b64":"qSs5h1nZJg7/YZk7POrIHLRr/mBC6BazwoviwSQf4Q8apNocaEYNBqIw5zDqK2nyDgOk9e/r1jBfvc5qr4+gDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b0e666a9a9d534907b7f790e0ea096bc777348344802ff83ff16f9f946d43b4","last_reissued_at":"2026-07-05T11:44:53.087274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:53.087274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Wenjie Zhu, Wenjun Zeng, Xin Jin, Yabin Zhang","submitted_at":"2025-07-26T07:44:04Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for building reliable machine learning models. Although negative prompt tuning has enhanced the OOD detection capabilities of vision-language models, these tuned models often suffer from reduced generalization performance on unseen classes and styles. To address this challenge, we propose a novel method called Knowledge Regularized Negative Feature Tuning (KR-NFT), which integrates an innovative adaptation architecture termed Negative Feature Tuning (NFT) and a corresponding knowledge-regularization (KR) optimization strategy. Specifically, NFT ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19847","kind":"arxiv","version":2},"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/2507.19847/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":"2507.19847","created_at":"2026-07-05T11:44:53.087351+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19847v2","created_at":"2026-07-05T11:44:53.087351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19847","created_at":"2026-07-05T11:44:53.087351+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMHGM2U2TVJU","created_at":"2026-07-05T11:44:53.087351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMHGM2U2TVJUSB5X","created_at":"2026-07-05T11:44:53.087351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMHGM2U2","created_at":"2026-07-05T11:44:53.087351+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/RMHGM2U2TVJUSB5X66IOB2QJNP","json":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP.json","graph_json":"https://pith.science/api/pith-number/RMHGM2U2TVJUSB5X66IOB2QJNP/graph.json","events_json":"https://pith.science/api/pith-number/RMHGM2U2TVJUSB5X66IOB2QJNP/events.json","paper":"https://pith.science/paper/RMHGM2U2"},"agent_actions":{"view_html":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP","download_json":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP.json","view_paper":"https://pith.science/paper/RMHGM2U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19847&json=true","fetch_graph":"https://pith.science/api/pith-number/RMHGM2U2TVJUSB5X66IOB2QJNP/graph.json","fetch_events":"https://pith.science/api/pith-number/RMHGM2U2TVJUSB5X66IOB2QJNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP/action/storage_attestation","attest_author":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP/action/author_attestation","sign_citation":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP/action/citation_signature","submit_replication":"https://pith.science/pith/RMHGM2U2TVJUSB5X66IOB2QJNP/action/replication_record"}},"created_at":"2026-07-05T11:44:53.087351+00:00","updated_at":"2026-07-05T11:44:53.087351+00:00"}