{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TAYJQZJHQ7R5UC4C2IAZSAFHPO","short_pith_number":"pith:TAYJQZJH","schema_version":"1.0","canonical_sha256":"983098652787e3da0b82d2019900a77b85b3416f1a69cb78460cbf4fb1a36cc0","source":{"kind":"arxiv","id":"2403.13684","version":3},"attestation_state":"computed","paper":{"title":"SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongjun Wang, Kai Han, Sagar Vaze","submitted_at":"2024-03-20T15:41:39Z","abstract_excerpt":"Generalized Category Discovery (GCD) aims to classify unlabelled images from both `seen' and `unseen' classes by transferring knowledge from a set of labelled `seen' class images. A key theme in existing GCD approaches is adapting large-scale pre-trained models for the GCD task. An alternate perspective, however, is to adapt the data representation itself for better alignment with the pre-trained model. As such, in this paper, we introduce a two-stage adaptation approach termed SPTNet, which iteratively optimizes model parameters (i.e., model-finetuning) and data parameters (i.e., prompt learn"},"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":"2403.13684","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T15:41:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e467d71ca3a6296827867b0b073fe8ec791b86983a7d11277f77e8a2aa6b404a","abstract_canon_sha256":"c07187e8a1e89d34fbc101c9a86b9c91a78c21c51b728adcfba28b6d68d7567c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:37.373632Z","signature_b64":"Dwv45EBJJpaI+XOwCe5Mk9cSSuS/jE1kvLwy3IFx9u6lOOry2PsUEMgM/dCVOnMw/8h1wWsCBme3OYFLF9HbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"983098652787e3da0b82d2019900a77b85b3416f1a69cb78460cbf4fb1a36cc0","last_reissued_at":"2026-07-05T10:34:37.372927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:37.372927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongjun Wang, Kai Han, Sagar Vaze","submitted_at":"2024-03-20T15:41:39Z","abstract_excerpt":"Generalized Category Discovery (GCD) aims to classify unlabelled images from both `seen' and `unseen' classes by transferring knowledge from a set of labelled `seen' class images. A key theme in existing GCD approaches is adapting large-scale pre-trained models for the GCD task. An alternate perspective, however, is to adapt the data representation itself for better alignment with the pre-trained model. As such, in this paper, we introduce a two-stage adaptation approach termed SPTNet, which iteratively optimizes model parameters (i.e., model-finetuning) and data parameters (i.e., prompt learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13684","kind":"arxiv","version":3},"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/2403.13684/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":"2403.13684","created_at":"2026-07-05T10:34:37.373002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13684v3","created_at":"2026-07-05T10:34:37.373002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13684","created_at":"2026-07-05T10:34:37.373002+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAYJQZJHQ7R5","created_at":"2026-07-05T10:34:37.373002+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAYJQZJHQ7R5UC4C","created_at":"2026-07-05T10:34:37.373002+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAYJQZJH","created_at":"2026-07-05T10:34:37.373002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00620","citing_title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","ref_index":91,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08183","citing_title":"Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery","ref_index":2,"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":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO","json":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO.json","graph_json":"https://pith.science/api/pith-number/TAYJQZJHQ7R5UC4C2IAZSAFHPO/graph.json","events_json":"https://pith.science/api/pith-number/TAYJQZJHQ7R5UC4C2IAZSAFHPO/events.json","paper":"https://pith.science/paper/TAYJQZJH"},"agent_actions":{"view_html":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO","download_json":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO.json","view_paper":"https://pith.science/paper/TAYJQZJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13684&json=true","fetch_graph":"https://pith.science/api/pith-number/TAYJQZJHQ7R5UC4C2IAZSAFHPO/graph.json","fetch_events":"https://pith.science/api/pith-number/TAYJQZJHQ7R5UC4C2IAZSAFHPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO/action/storage_attestation","attest_author":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO/action/author_attestation","sign_citation":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO/action/citation_signature","submit_replication":"https://pith.science/pith/TAYJQZJHQ7R5UC4C2IAZSAFHPO/action/replication_record"}},"created_at":"2026-07-05T10:34:37.373002+00:00","updated_at":"2026-07-05T10:34:37.373002+00:00"}