{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7IHO7F3GPT6JSBZBMIWMZJGHVI","short_pith_number":"pith:7IHO7F3G","schema_version":"1.0","canonical_sha256":"fa0eef97667cfc990721622ccca4c7aa3ec5ca8e5cdfd4289ee10b716005b2af","source":{"kind":"arxiv","id":"2505.23045","version":1},"attestation_state":"computed","paper":{"title":"Multi-Sourced Compositional Generalization in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Wenbo Ye, Yunde Jia, Yuwei Wu, Zhen Li","submitted_at":"2025-05-29T03:41:36Z","abstract_excerpt":"Compositional generalization is the ability of generalizing novel compositions from seen primitives, and has received much attention in vision-and-language (V\\&L) recently. Due to the multi-modal nature of V\\&L tasks, the primitives composing compositions source from different modalities, resulting in multi-sourced novel compositions. However, the generalization ability over multi-sourced novel compositions, \\textit{i.e.}, multi-sourced compositional generalization (MSCG) remains unexplored. In this paper, we explore MSCG in the context of visual question answering (VQA), and propose a retriev"},"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":"2505.23045","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:41:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11931f177b79ec5970e45324e82a35f055dfbcb778f49b576977403df2c083ca","abstract_canon_sha256":"f408c74f3d781fe8bddc012688fffc866c7a7a1a55b21c86cd5f4682d9705b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:54.287873Z","signature_b64":"MqQ/j3sQKOEus6nI5c0ZfF/NnNI1FOZmVk2RPqg3iNxgDZgVgSoZGXpTw0+57hYYCeGfkYqTj4E5vFvnF1JkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa0eef97667cfc990721622ccca4c7aa3ec5ca8e5cdfd4289ee10b716005b2af","last_reissued_at":"2026-07-05T11:11:54.287379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:54.287379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Sourced Compositional Generalization in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Wenbo Ye, Yunde Jia, Yuwei Wu, Zhen Li","submitted_at":"2025-05-29T03:41:36Z","abstract_excerpt":"Compositional generalization is the ability of generalizing novel compositions from seen primitives, and has received much attention in vision-and-language (V\\&L) recently. Due to the multi-modal nature of V\\&L tasks, the primitives composing compositions source from different modalities, resulting in multi-sourced novel compositions. However, the generalization ability over multi-sourced novel compositions, \\textit{i.e.}, multi-sourced compositional generalization (MSCG) remains unexplored. In this paper, we explore MSCG in the context of visual question answering (VQA), and propose a retriev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23045","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/2505.23045/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":"2505.23045","created_at":"2026-07-05T11:11:54.287438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23045v1","created_at":"2026-07-05T11:11:54.287438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23045","created_at":"2026-07-05T11:11:54.287438+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IHO7F3GPT6J","created_at":"2026-07-05T11:11:54.287438+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IHO7F3GPT6JSBZB","created_at":"2026-07-05T11:11:54.287438+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IHO7F3G","created_at":"2026-07-05T11:11:54.287438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI","json":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI.json","graph_json":"https://pith.science/api/pith-number/7IHO7F3GPT6JSBZBMIWMZJGHVI/graph.json","events_json":"https://pith.science/api/pith-number/7IHO7F3GPT6JSBZBMIWMZJGHVI/events.json","paper":"https://pith.science/paper/7IHO7F3G"},"agent_actions":{"view_html":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI","download_json":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI.json","view_paper":"https://pith.science/paper/7IHO7F3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23045&json=true","fetch_graph":"https://pith.science/api/pith-number/7IHO7F3GPT6JSBZBMIWMZJGHVI/graph.json","fetch_events":"https://pith.science/api/pith-number/7IHO7F3GPT6JSBZBMIWMZJGHVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI/action/storage_attestation","attest_author":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI/action/author_attestation","sign_citation":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI/action/citation_signature","submit_replication":"https://pith.science/pith/7IHO7F3GPT6JSBZBMIWMZJGHVI/action/replication_record"}},"created_at":"2026-07-05T11:11:54.287438+00:00","updated_at":"2026-07-05T11:11:54.287438+00:00"}