{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MSDIYUTCBBHTGI7C4TSCTNIB6Y","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":"3c02ecad2df21d13116fb41d6097f3eed70f41d238811969940192fb67fd7d63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T08:58:10Z","title_canon_sha256":"a6d673f5378f5815d58f033ea7137600db0ab217fc8d0d2ddfb22770a435a7bf"},"schema_version":"1.0","source":{"id":"2509.20912","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20912","created_at":"2026-05-21T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20912v3","created_at":"2026-05-21T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20912","created_at":"2026-05-21T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"MSDIYUTCBBHT","created_at":"2026-05-21T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"MSDIYUTCBBHTGI7C","created_at":"2026-05-21T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"MSDIYUTC","created_at":"2026-05-21T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:cdd89b7d736b7e04b24d4feb7a902d74f659ad91dca7453e2fe2a125d2a1635b","target":"graph","created_at":"2026-05-21T01:05:09Z","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/2509.20912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal language models (MLLMs) have made thinking with images a dominant paradigm for multimodal reasoning. However, existing methods still fail to ensure evidence-answer consistency, where correct answers must be supported by correct visual evidence. To address this issue, we propose DeFacto, a counterfactual reasoning framework that explicitly aligns visual evidence with final answers. Our approach integrates three complementary training paradigms: positive, counterfactual, and random-masking. We further develop a language-guided evidence construction pipeline that aut","authors_text":"Feng Chen, Guanyu Chen, Haichuan Gao, Haoda Jing, Jun Feng, Tianren Zhang, Tianrun Xu, Ye Li, Yuquan Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T08:58:10Z","title":"DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20912","kind":"arxiv","version":3},"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":"sha256:39f0e13283197c675463f6c7730110ad57c92cbc8dd0981e2bfbe19afa352a56","target":"record","created_at":"2026-05-21T01:05:09Z","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":"3c02ecad2df21d13116fb41d6097f3eed70f41d238811969940192fb67fd7d63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T08:58:10Z","title_canon_sha256":"a6d673f5378f5815d58f033ea7137600db0ab217fc8d0d2ddfb22770a435a7bf"},"schema_version":"1.0","source":{"id":"2509.20912","kind":"arxiv","version":3}},"canonical_sha256":"64868c5262084f3323e2e4e429b501f611d2374af3c31e26f1105a63dd1d72d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64868c5262084f3323e2e4e429b501f611d2374af3c31e26f1105a63dd1d72d1","first_computed_at":"2026-05-21T01:05:09.479839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:09.479839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dO0SIzaypQg5uZ8kzM5SJ/bRXQnrUYjw4yPPlSo18OHqnawyXQ8AbCFBX3CZDhkJ3y79kJ+LSErceJDi3phzBA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:09.480808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.20912","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39f0e13283197c675463f6c7730110ad57c92cbc8dd0981e2bfbe19afa352a56","sha256:cdd89b7d736b7e04b24d4feb7a902d74f659ad91dca7453e2fe2a125d2a1635b"],"state_sha256":"0925ed06119d8d4649dddee9406288d455ae3a1ee79a797e4281093a90f0459c"}