{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PJ2KYOQGLYMJQ3ZLGKSLVGOV6D","short_pith_number":"pith:PJ2KYOQG","schema_version":"1.0","canonical_sha256":"7a74ac3a065e18986f2b32a4ba99d5f0d431c15acb413a3000960ed0648082d7","source":{"kind":"arxiv","id":"2306.02240","version":2},"attestation_state":"computed","paper":{"title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chih-Hui Ho, Nuno Vasconcelos, Tz-Ying Wu","submitted_at":"2023-06-04T02:55:25Z","abstract_excerpt":"Visual-language foundation models, like CLIP, learn generalized representations that enable zero-shot open-set classification. Few-shot adaptation methods, based on prompt tuning, have been shown to further improve performance on downstream datasets. However, these methods do not fare well in the taxonomic open set (TOS) setting, where the classifier is asked to make predictions from label sets across different levels of semantic granularity. Frequently, they infer incorrect labels at coarser taxonomic class levels, even when the inference at the leaf level (original class labels) is correct. "},"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":"2306.02240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T02:55:25Z","cross_cats_sorted":[],"title_canon_sha256":"a8c2cb6add2f69790dded4863dd1fab9071493cb111afa32895dc95b43fdc151","abstract_canon_sha256":"e38e435729075cb81b5ff58eb89f8ff7f50a85eb7947c7e6a07d108432b195a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:30.452224Z","signature_b64":"TVm0VJfDi6t7l+ea5aj2SmUPiPe+f6EuKfMHiNNA7sosD0wipSIhu8SS7momoBCBASgHnZwsTMMeGKQG4Di6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a74ac3a065e18986f2b32a4ba99d5f0d431c15acb413a3000960ed0648082d7","last_reissued_at":"2026-07-05T08:01:30.451750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:30.451750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chih-Hui Ho, Nuno Vasconcelos, Tz-Ying Wu","submitted_at":"2023-06-04T02:55:25Z","abstract_excerpt":"Visual-language foundation models, like CLIP, learn generalized representations that enable zero-shot open-set classification. Few-shot adaptation methods, based on prompt tuning, have been shown to further improve performance on downstream datasets. However, these methods do not fare well in the taxonomic open set (TOS) setting, where the classifier is asked to make predictions from label sets across different levels of semantic granularity. Frequently, they infer incorrect labels at coarser taxonomic class levels, even when the inference at the leaf level (original class labels) is correct. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02240","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/2306.02240/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":"2306.02240","created_at":"2026-07-05T08:01:30.451815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02240v2","created_at":"2026-07-05T08:01:30.451815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02240","created_at":"2026-07-05T08:01:30.451815+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ2KYOQGLYMJ","created_at":"2026-07-05T08:01:30.451815+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ2KYOQGLYMJQ3ZL","created_at":"2026-07-05T08:01:30.451815+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ2KYOQG","created_at":"2026-07-05T08:01:30.451815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21348","citing_title":"PanSt3R: Multi-view Consistent Panoptic Segmentation","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D","json":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D.json","graph_json":"https://pith.science/api/pith-number/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/graph.json","events_json":"https://pith.science/api/pith-number/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/events.json","paper":"https://pith.science/paper/PJ2KYOQG"},"agent_actions":{"view_html":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D","download_json":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D.json","view_paper":"https://pith.science/paper/PJ2KYOQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02240&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/action/storage_attestation","attest_author":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/action/author_attestation","sign_citation":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/action/citation_signature","submit_replication":"https://pith.science/pith/PJ2KYOQGLYMJQ3ZLGKSLVGOV6D/action/replication_record"}},"created_at":"2026-07-05T08:01:30.451815+00:00","updated_at":"2026-07-05T08:01:30.451815+00:00"}