{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3EOSWYHRGIQKXYAOMQBEOYYXMZ","short_pith_number":"pith:3EOSWYHR","schema_version":"1.0","canonical_sha256":"d91d2b60f13220abe00e64024763176649b0af67123ad77079649da4d6acf33f","source":{"kind":"arxiv","id":"2409.11624","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Generalized Category Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Min Xu, Renping Zhou, Siyu Huang, Tianyang Wang, Xingjian Li, Yuchang Su, Ziyue Wang","submitted_at":"2024-09-18T01:08:49Z","abstract_excerpt":"Generalized Category Discovery (GCD) aims to classify inputs into both known and novel categories, a task crucial for open-world scientific discoveries. However, current GCD methods are limited to unimodal data, overlooking the inherently multimodal nature of most real-world data. In this work, we extend GCD to a multimodal setting, where inputs from different modalities provide richer and complementary information. Through theoretical analysis and empirical validation, we identify that the key challenge in multimodal GCD lies in effectively aligning heterogeneous information across modalities"},"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":"2409.11624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-18T01:08:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d94619adf9e99646a76cc4d8bb233fe642f8b53c2073d7e06104dddc1009655e","abstract_canon_sha256":"0471589fbb7e78d7bc7f4aa401ac6eb3c418b4d49721858c90aaba3535b456c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:34.824068Z","signature_b64":"ZMey5rGCPDj2TnBGtszzuJFJQ362VWGkQzgE9niPiek9CyjumB4xoz6/RwN+nUT2jcuarxQPdsEhgy68FOwxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d91d2b60f13220abe00e64024763176649b0af67123ad77079649da4d6acf33f","last_reissued_at":"2026-07-05T09:08:34.823608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:34.823608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Generalized Category Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Min Xu, Renping Zhou, Siyu Huang, Tianyang Wang, Xingjian Li, Yuchang Su, Ziyue Wang","submitted_at":"2024-09-18T01:08:49Z","abstract_excerpt":"Generalized Category Discovery (GCD) aims to classify inputs into both known and novel categories, a task crucial for open-world scientific discoveries. However, current GCD methods are limited to unimodal data, overlooking the inherently multimodal nature of most real-world data. In this work, we extend GCD to a multimodal setting, where inputs from different modalities provide richer and complementary information. Through theoretical analysis and empirical validation, we identify that the key challenge in multimodal GCD lies in effectively aligning heterogeneous information across modalities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11624","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/2409.11624/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":"2409.11624","created_at":"2026-07-05T09:08:34.823667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11624v1","created_at":"2026-07-05T09:08:34.823667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11624","created_at":"2026-07-05T09:08:34.823667+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EOSWYHRGIQK","created_at":"2026-07-05T09:08:34.823667+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EOSWYHRGIQKXYAO","created_at":"2026-07-05T09:08:34.823667+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EOSWYHR","created_at":"2026-07-05T09:08:34.823667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00620","citing_title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","ref_index":55,"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":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ","json":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ.json","graph_json":"https://pith.science/api/pith-number/3EOSWYHRGIQKXYAOMQBEOYYXMZ/graph.json","events_json":"https://pith.science/api/pith-number/3EOSWYHRGIQKXYAOMQBEOYYXMZ/events.json","paper":"https://pith.science/paper/3EOSWYHR"},"agent_actions":{"view_html":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ","download_json":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ.json","view_paper":"https://pith.science/paper/3EOSWYHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11624&json=true","fetch_graph":"https://pith.science/api/pith-number/3EOSWYHRGIQKXYAOMQBEOYYXMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3EOSWYHRGIQKXYAOMQBEOYYXMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ/action/storage_attestation","attest_author":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ/action/author_attestation","sign_citation":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ/action/citation_signature","submit_replication":"https://pith.science/pith/3EOSWYHRGIQKXYAOMQBEOYYXMZ/action/replication_record"}},"created_at":"2026-07-05T09:08:34.823667+00:00","updated_at":"2026-07-05T09:08:34.823667+00:00"}