{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KJ7QF4KWN3B3MKSYSI6NED64BG","short_pith_number":"pith:KJ7QF4KW","schema_version":"1.0","canonical_sha256":"527f02f1566ec3b62a58923cd20fdc09949eeef1c571df3fbe23d493ae43aed3","source":{"kind":"arxiv","id":"2507.14935","version":1},"attestation_state":"computed","paper":{"title":"Open-set Cross Modal Generalization via Multimodal Unified Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai Huang, Hanting Wang, Minghui Fang, Sashuai Zhou, Shengpeng Ji, Shulei Wang, Tao Jin, Yan Xia, Zhou Zhao","submitted_at":"2025-07-20T12:09:19Z","abstract_excerpt":"This paper extends Cross Modal Generalization (CMG) to open-set environments by proposing the more challenging Open-set Cross Modal Generalization (OSCMG) task. This task evaluates multimodal unified representations in open-set conditions, addressing the limitations of prior closed-set cross-modal evaluations. OSCMG requires not only cross-modal knowledge transfer but also robust generalization to unseen classes within new modalities, a scenario frequently encountered in real-world applications. Existing multimodal unified representation work lacks consideration for open-set environments. To t"},"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":"2507.14935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-20T12:09:19Z","cross_cats_sorted":[],"title_canon_sha256":"12ecb11a8038a10cecf9d709b70065d75c2b328b429cc96fc9de8a5b64425368","abstract_canon_sha256":"2c967b2ba8e3b4e2ab50c35dee5b25dfee041d36f176e5fe84fd0c4779d8941a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:15.712595Z","signature_b64":"ygu3ooxDrs/sdu/56UqbQOwszmilJbLrBmThbY1r4VRn8Q7wudsMRUggQtAfcuixOOc5qEW7qKGKt6Kk+1drCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"527f02f1566ec3b62a58923cd20fdc09949eeef1c571df3fbe23d493ae43aed3","last_reissued_at":"2026-07-05T11:40:15.712066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:15.712066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-set Cross Modal Generalization via Multimodal Unified Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai Huang, Hanting Wang, Minghui Fang, Sashuai Zhou, Shengpeng Ji, Shulei Wang, Tao Jin, Yan Xia, Zhou Zhao","submitted_at":"2025-07-20T12:09:19Z","abstract_excerpt":"This paper extends Cross Modal Generalization (CMG) to open-set environments by proposing the more challenging Open-set Cross Modal Generalization (OSCMG) task. This task evaluates multimodal unified representations in open-set conditions, addressing the limitations of prior closed-set cross-modal evaluations. OSCMG requires not only cross-modal knowledge transfer but also robust generalization to unseen classes within new modalities, a scenario frequently encountered in real-world applications. Existing multimodal unified representation work lacks consideration for open-set environments. To t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14935","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/2507.14935/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":"2507.14935","created_at":"2026-07-05T11:40:15.712135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14935v1","created_at":"2026-07-05T11:40:15.712135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14935","created_at":"2026-07-05T11:40:15.712135+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJ7QF4KWN3B3","created_at":"2026-07-05T11:40:15.712135+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJ7QF4KWN3B3MKSY","created_at":"2026-07-05T11:40:15.712135+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJ7QF4KW","created_at":"2026-07-05T11:40:15.712135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07878","citing_title":"TAP: Parameter-efficient Task-Aware Prompting for Adverse Weather Removal","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG","json":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG.json","graph_json":"https://pith.science/api/pith-number/KJ7QF4KWN3B3MKSYSI6NED64BG/graph.json","events_json":"https://pith.science/api/pith-number/KJ7QF4KWN3B3MKSYSI6NED64BG/events.json","paper":"https://pith.science/paper/KJ7QF4KW"},"agent_actions":{"view_html":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG","download_json":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG.json","view_paper":"https://pith.science/paper/KJ7QF4KW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14935&json=true","fetch_graph":"https://pith.science/api/pith-number/KJ7QF4KWN3B3MKSYSI6NED64BG/graph.json","fetch_events":"https://pith.science/api/pith-number/KJ7QF4KWN3B3MKSYSI6NED64BG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG/action/storage_attestation","attest_author":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG/action/author_attestation","sign_citation":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG/action/citation_signature","submit_replication":"https://pith.science/pith/KJ7QF4KWN3B3MKSYSI6NED64BG/action/replication_record"}},"created_at":"2026-07-05T11:40:15.712135+00:00","updated_at":"2026-07-05T11:40:15.712135+00:00"}