{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OJAM2Q6JD2YRHFC2VZNNYKV6BO","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":"0d3af62990cb33ea3d88104542d002a7a797a23281df2d19d2a3dbd23779890a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T19:05:45Z","title_canon_sha256":"2926e39d81b928e0be047e2c71e81ba53af7d47595da3f02e37a85c6b19cf6cc"},"schema_version":"1.0","source":{"id":"2502.14044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14044","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14044v2","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14044","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"OJAM2Q6JD2YR","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"OJAM2Q6JD2YRHFC2","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"OJAM2Q6J","created_at":"2026-07-05T10:19:39Z"}],"graph_snapshots":[{"event_id":"sha256:b356176e635abbf80099e61a81602596bf6fc77993708761633e8b0662f59c2f","target":"graph","created_at":"2026-07-05T10:19:39Z","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/2502.14044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific objectives and provide justifiable explanations for their predictions. To address the above challenge, we propose a novel visual rejection sampling framework to improve the cognition and explainability of LMMs using self-synthesized data. Specifically, visual fine-tuning requires images, queries, and target answers. Our approach begins by synthesizing interpretab","authors_text":"Jin Sun, Ninghao Liu, Quanzheng Li, Xiang Li, Yucheng Shi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T19:05:45Z","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14044","kind":"arxiv","version":2},"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":"sha256:84e1853f7c9b775132162281a5051dbcb7690f21c78b53d15201e80b15d94b9e","target":"record","created_at":"2026-07-05T10:19:39Z","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":"0d3af62990cb33ea3d88104542d002a7a797a23281df2d19d2a3dbd23779890a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T19:05:45Z","title_canon_sha256":"2926e39d81b928e0be047e2c71e81ba53af7d47595da3f02e37a85c6b19cf6cc"},"schema_version":"1.0","source":{"id":"2502.14044","kind":"arxiv","version":2}},"canonical_sha256":"7240cd43c91eb113945aae5adc2abe0bbe2e34db9c4c128bd6c9d94066e784ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7240cd43c91eb113945aae5adc2abe0bbe2e34db9c4c128bd6c9d94066e784ca","first_computed_at":"2026-07-05T10:19:39.643102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:39.643102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3WU2vyZ4LT8hjhFWaUBfZcnsLrrk3ioWO7wEc0kcmdl7/ZHoZ9Mxc+4J04VpCyTJjVw0CGTQlVV3AvQuaf+ZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:39.643601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84e1853f7c9b775132162281a5051dbcb7690f21c78b53d15201e80b15d94b9e","sha256:b356176e635abbf80099e61a81602596bf6fc77993708761633e8b0662f59c2f"],"state_sha256":"b16dc89774f07214851da64fb1a4e42091f2ad4ab9e875ffa926369d1f078e0a"}