{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:URJNJISIIJXTCBNR7LRGZIGJZQ","short_pith_number":"pith:URJNJISI","schema_version":"1.0","canonical_sha256":"a452d4a248426f3105b1fae26ca0c9cc2d8ae3bcea14758a0ddb103940194323","source":{"kind":"arxiv","id":"2506.17633","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arvind Easwaran, Blaise Genest, Xiang Fang","submitted_at":"2025-06-21T08:31:29Z","abstract_excerpt":"Out-of-distribution (OOD) detection attempts to distinguish outlier samples to prevent models trained on the in-distribution (ID) dataset from producing unavailable outputs. Most OOD detection methods require many IID samples for training, which seriously limits their real-world applications. To this end, we target a challenging setting: few-shot OOD detection, where {Only a few {\\em labeled ID} samples are available.} Therefore, few-shot OOD detection is much more challenging than the traditional OOD detection setting. Previous few-shot OOD detection works ignore the distinct diversity betwee"},"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":"2506.17633","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-21T08:31:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecbff6c7c6460a0cf112e8c221f23a423325c0cf3eabd4b9c1dddc2fec416d6f","abstract_canon_sha256":"f614e0a6887b514bc31a2725dad211e9681f56061d663a2f58e50ee03ebbea08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T00:04:24.155326Z","signature_b64":"vpmVt+5SIc0WpEIURoTNF3D/P+h3SJaqOhmkK5dLrhAJxD3CuuHYiARNWVIc9nAFD7kbct4tBrqBs/RLO8RgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a452d4a248426f3105b1fae26ca0c9cc2d8ae3bcea14758a0ddb103940194323","last_reissued_at":"2026-05-27T00:04:24.154591Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T00:04:24.154591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arvind Easwaran, Blaise Genest, Xiang Fang","submitted_at":"2025-06-21T08:31:29Z","abstract_excerpt":"Out-of-distribution (OOD) detection attempts to distinguish outlier samples to prevent models trained on the in-distribution (ID) dataset from producing unavailable outputs. Most OOD detection methods require many IID samples for training, which seriously limits their real-world applications. To this end, we target a challenging setting: few-shot OOD detection, where {Only a few {\\em labeled ID} samples are available.} Therefore, few-shot OOD detection is much more challenging than the traditional OOD detection setting. Previous few-shot OOD detection works ignore the distinct diversity betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17633","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/2506.17633/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":"2506.17633","created_at":"2026-05-27T00:04:24.154664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17633v2","created_at":"2026-05-27T00:04:24.154664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17633","created_at":"2026-05-27T00:04:24.154664+00:00"},{"alias_kind":"pith_short_12","alias_value":"URJNJISIIJXT","created_at":"2026-05-27T00:04:24.154664+00:00"},{"alias_kind":"pith_short_16","alias_value":"URJNJISIIJXTCBNR","created_at":"2026-05-27T00:04:24.154664+00:00"},{"alias_kind":"pith_short_8","alias_value":"URJNJISI","created_at":"2026-05-27T00:04:24.154664+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/URJNJISIIJXTCBNR7LRGZIGJZQ","json":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ.json","graph_json":"https://pith.science/api/pith-number/URJNJISIIJXTCBNR7LRGZIGJZQ/graph.json","events_json":"https://pith.science/api/pith-number/URJNJISIIJXTCBNR7LRGZIGJZQ/events.json","paper":"https://pith.science/paper/URJNJISI"},"agent_actions":{"view_html":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ","download_json":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ.json","view_paper":"https://pith.science/paper/URJNJISI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17633&json=true","fetch_graph":"https://pith.science/api/pith-number/URJNJISIIJXTCBNR7LRGZIGJZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/URJNJISIIJXTCBNR7LRGZIGJZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ/action/storage_attestation","attest_author":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ/action/author_attestation","sign_citation":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ/action/citation_signature","submit_replication":"https://pith.science/pith/URJNJISIIJXTCBNR7LRGZIGJZQ/action/replication_record"}},"created_at":"2026-05-27T00:04:24.154664+00:00","updated_at":"2026-05-27T00:04:24.154664+00:00"}