{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7IHO7F3GPT6JSBZBMIWMZJGHVI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f408c74f3d781fe8bddc012688fffc866c7a7a1a55b21c86cd5f4682d9705b27","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:41:36Z","title_canon_sha256":"11931f177b79ec5970e45324e82a35f055dfbcb778f49b576977403df2c083ca"},"schema_version":"1.0","source":{"id":"2505.23045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23045","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23045v1","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23045","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_12","alias_value":"7IHO7F3GPT6J","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_16","alias_value":"7IHO7F3GPT6JSBZB","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_8","alias_value":"7IHO7F3G","created_at":"2026-07-05T11:11:54Z"}],"graph_snapshots":[{"event_id":"sha256:cd51c0efe0ef3aca315d3565071cc4cacd61f8211d8636ed8edeca27dfa3468c","target":"graph","created_at":"2026-07-05T11:11:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.23045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chuanhao Li, Wenbo Ye, Yunde Jia, Yuwei Wu, Zhen Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:41:36Z","title":"Multi-Sourced Compositional Generalization in Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23045","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ea1aab66b7f1a49ec26dacabd9b216085fbb486f9e73e507f8ff666a58255069","target":"record","created_at":"2026-07-05T11:11:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f408c74f3d781fe8bddc012688fffc866c7a7a1a55b21c86cd5f4682d9705b27","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:41:36Z","title_canon_sha256":"11931f177b79ec5970e45324e82a35f055dfbcb778f49b576977403df2c083ca"},"schema_version":"1.0","source":{"id":"2505.23045","kind":"arxiv","version":1}},"canonical_sha256":"fa0eef97667cfc990721622ccca4c7aa3ec5ca8e5cdfd4289ee10b716005b2af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa0eef97667cfc990721622ccca4c7aa3ec5ca8e5cdfd4289ee10b716005b2af","first_computed_at":"2026-07-05T11:11:54.287379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:54.287379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MqQ/j3sQKOEus6nI5c0ZfF/NnNI1FOZmVk2RPqg3iNxgDZgVgSoZGXpTw0+57hYYCeGfkYqTj4E5vFvnF1JkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:54.287873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea1aab66b7f1a49ec26dacabd9b216085fbb486f9e73e507f8ff666a58255069","sha256:cd51c0efe0ef3aca315d3565071cc4cacd61f8211d8636ed8edeca27dfa3468c"],"state_sha256":"ead98011530f3fede5e07af85ab2a3fdb5872d641fa0a9f074e2fb8d53ad671f"}