{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NZH76WEONIO6JAME3OEJXHRQBU","short_pith_number":"pith:NZH76WEO","schema_version":"1.0","canonical_sha256":"6e4fff588e6a1de48184db889b9e300d295aa97c64b7f3152631fd374146393f","source":{"kind":"arxiv","id":"2305.10420","version":1},"attestation_state":"computed","paper":{"title":"CLIP-GCD: Simple Language Guided Generalized Category Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chia-Wen Kuo, Rabah Ouldnoughi, Zsolt Kira","submitted_at":"2023-05-17T17:55:33Z","abstract_excerpt":"Generalized Category Discovery (GCD) requires a model to both classify known categories and cluster unknown categories in unlabeled data. Prior methods leveraged self-supervised pre-training combined with supervised fine-tuning on the labeled data, followed by simple clustering methods. In this paper, we posit that such methods are still prone to poor performance on out-of-distribution categories, and do not leverage a key ingredient: Semantic relationships between object categories. We therefore propose to leverage multi-modal (vision and language) models, in two complementary ways. First, we"},"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":"2305.10420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T17:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"1c1b941e706e8124c6b4ce9c8ba259c3e23f81387843ec1c926f4da8d5787c17","abstract_canon_sha256":"eea2c35d9ccbce4073e3d44e5bb875922bf65c3b993320d425b6e85ad2925535"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:14.234149Z","signature_b64":"503Cwmh8ZxjqYzUj12fiigN+KJ9JylHxzD/gkSIZvOZL5xVfZ2lUbm0vrGf+wedLIDI142HRaQt+9VkcsKWvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e4fff588e6a1de48184db889b9e300d295aa97c64b7f3152631fd374146393f","last_reissued_at":"2026-07-05T06:11:14.232330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:14.232330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-GCD: Simple Language Guided Generalized Category Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chia-Wen Kuo, Rabah Ouldnoughi, Zsolt Kira","submitted_at":"2023-05-17T17:55:33Z","abstract_excerpt":"Generalized Category Discovery (GCD) requires a model to both classify known categories and cluster unknown categories in unlabeled data. Prior methods leveraged self-supervised pre-training combined with supervised fine-tuning on the labeled data, followed by simple clustering methods. In this paper, we posit that such methods are still prone to poor performance on out-of-distribution categories, and do not leverage a key ingredient: Semantic relationships between object categories. We therefore propose to leverage multi-modal (vision and language) models, in two complementary ways. First, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10420","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/2305.10420/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":"2305.10420","created_at":"2026-07-05T06:11:14.232395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10420v1","created_at":"2026-07-05T06:11:14.232395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10420","created_at":"2026-07-05T06:11:14.232395+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZH76WEONIO6","created_at":"2026-07-05T06:11:14.232395+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZH76WEONIO6JAME","created_at":"2026-07-05T06:11:14.232395+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZH76WEO","created_at":"2026-07-05T06:11:14.232395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21446","citing_title":"Synergistic Dual-Branch Adaptation for Multi-modal Generalized Category Discovery","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00620","citing_title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14176","citing_title":"The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27596","citing_title":"SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00906","citing_title":"Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11484","citing_title":"PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU","json":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU.json","graph_json":"https://pith.science/api/pith-number/NZH76WEONIO6JAME3OEJXHRQBU/graph.json","events_json":"https://pith.science/api/pith-number/NZH76WEONIO6JAME3OEJXHRQBU/events.json","paper":"https://pith.science/paper/NZH76WEO"},"agent_actions":{"view_html":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU","download_json":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU.json","view_paper":"https://pith.science/paper/NZH76WEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10420&json=true","fetch_graph":"https://pith.science/api/pith-number/NZH76WEONIO6JAME3OEJXHRQBU/graph.json","fetch_events":"https://pith.science/api/pith-number/NZH76WEONIO6JAME3OEJXHRQBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU/action/storage_attestation","attest_author":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU/action/author_attestation","sign_citation":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU/action/citation_signature","submit_replication":"https://pith.science/pith/NZH76WEONIO6JAME3OEJXHRQBU/action/replication_record"}},"created_at":"2026-07-05T06:11:14.232395+00:00","updated_at":"2026-07-05T06:11:14.232395+00:00"}