{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:44ZQTYURYSAA2MOKO64OMYX5QX","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":"80311ba9daf694895e35b7a21fb6534caa733a477fa4ced5fa6a89cfa5e3ecdd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T09:02:10Z","title_canon_sha256":"8d1190318fe1bede41dbe60865c637ed0b4562b43af4f85b0fd739537d42b09c"},"schema_version":"1.0","source":{"id":"2608.08021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08021","created_at":"2026-08-11T01:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08021v1","created_at":"2026-08-11T01:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08021","created_at":"2026-08-11T01:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"44ZQTYURYSAA","created_at":"2026-08-11T01:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"44ZQTYURYSAA2MOK","created_at":"2026-08-11T01:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"44ZQTYUR","created_at":"2026-08-11T01:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:d17c77ce5ece18c45d6b040837def37f0aa2e8df469ab2bfb4265d482b45a5e3","target":"graph","created_at":"2026-08-11T01:21:25Z","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/2608.08021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing perception-aware post-training methods encourage image use through global perturbations or attention proxies, but they do not test whether a sampled answer causally depends on the local evidence that supports it. We propose Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding. For each response, CED neutralizes an object-centric Evidence Region and compares the resulting support drop against ma","authors_text":"Chengming Xu, Cheng Yang, Haojie Huang, Jiangning Zhang, Qingdong He, Xiaobin Hu, Xinlei Yu, Yu Yang, Zhangquan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T09:02:10Z","title":"Evidence-RL: Towards Evidence-intensive Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08021","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":"sha256:8ec1aa0f5cbb0c0013a9ce25322a9acad37c4b895ac4363819be1ed9e0bba343","target":"record","created_at":"2026-08-11T01:21:25Z","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":"80311ba9daf694895e35b7a21fb6534caa733a477fa4ced5fa6a89cfa5e3ecdd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T09:02:10Z","title_canon_sha256":"8d1190318fe1bede41dbe60865c637ed0b4562b43af4f85b0fd739537d42b09c"},"schema_version":"1.0","source":{"id":"2608.08021","kind":"arxiv","version":1}},"canonical_sha256":"e73309e291c4800d31ca77b8e662fd85cd6b04498c2ec363bdb9017731ddbb4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e73309e291c4800d31ca77b8e662fd85cd6b04498c2ec363bdb9017731ddbb4c","first_computed_at":"2026-08-11T01:21:25.466872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:21:25.466872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Kn/flkPPrNaTd7/AqgSoHVKydu/IvGHxhfcN35KfWUdDJv+/Xc4iuHgaWaMMuvnj88S57R9lpZujYN8J8EHCw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:21:25.469651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ec1aa0f5cbb0c0013a9ce25322a9acad37c4b895ac4363819be1ed9e0bba343","sha256:d17c77ce5ece18c45d6b040837def37f0aa2e8df469ab2bfb4265d482b45a5e3"],"state_sha256":"21513e3276786beb72dd8e2f0a8b14c004fd1249a90074d02c4d4d951f21a83c"}