{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JCY5BDII5LK4GJ5REIKLSKU5J4","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":"d1aa91c1f934ee84ef962848b203572fd246b3450ca31ab35a7f977c7fa40ac0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T07:27:02Z","title_canon_sha256":"433ddb6c1ab00940e3bcf8b8a408d2358d4f1417ba40dff615b29dd76ade71be"},"schema_version":"1.0","source":{"id":"2607.04149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04149","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04149v1","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04149","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"JCY5BDII5LK4","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"JCY5BDII5LK4GJ5R","created_at":"2026-07-07T02:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"JCY5BDII","created_at":"2026-07-07T02:18:59Z"}],"graph_snapshots":[{"event_id":"sha256:a0c2d0c7ce3a6296e20fbed0008928cca7566fdb0fbea0606adaa2e3de86ee61","target":"graph","created_at":"2026-07-07T02:18:59Z","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/2607.04149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In safety-critical traffic scenarios, answering complex questions relies on minute, localized visual cues. However, standard Multimodal Large Language Models (MLLMs) tend to over-attend to backgrounds, overwhelming crucial small objects during visual-language alignment, a failure mode we term 'critical evidence dilution.' Furthermore, existing visual question answering (VQA) datasets rarely expose this flaw, as they lack large-scale, distractor-heavy evaluations that require pinpointing local evidence. To bridge this evaluation and architecture gap, we introduce the Fine-Grained Traffic Reason","authors_text":"Chen Sun, Qiang Lu, Waikit Xiu, Xinjie Yang, Xiying Li, Zhiwei Chen, Zian Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T07:27:02Z","title":"Beyond Scene Priors: Fine-Grained Traffic Scene Reasoning with Benchmarking and Query-Guided Small-Object Focus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04149","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:e79e32cc33031e844a563bf6f1e8fd4cf4e6aac99aa02a652043cd95430ae0b2","target":"record","created_at":"2026-07-07T02:18:59Z","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":"d1aa91c1f934ee84ef962848b203572fd246b3450ca31ab35a7f977c7fa40ac0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T07:27:02Z","title_canon_sha256":"433ddb6c1ab00940e3bcf8b8a408d2358d4f1417ba40dff615b29dd76ade71be"},"schema_version":"1.0","source":{"id":"2607.04149","kind":"arxiv","version":1}},"canonical_sha256":"48b1d08d08ead5c327b12214b92a9d4f1dbd922c2ef88a66e621402202dc6c74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48b1d08d08ead5c327b12214b92a9d4f1dbd922c2ef88a66e621402202dc6c74","first_computed_at":"2026-07-07T02:18:59.814779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:59.814779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JB76exoOsVx1Id5c2ggMZLtXmvGgi64NUjl3xM8aicwcaA+v/L8staKnSI53LKpHL6ZvywoWnaKZCSBkN14SBw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:59.815489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e79e32cc33031e844a563bf6f1e8fd4cf4e6aac99aa02a652043cd95430ae0b2","sha256:a0c2d0c7ce3a6296e20fbed0008928cca7566fdb0fbea0606adaa2e3de86ee61"],"state_sha256":"7fe9c0c03c86c111efb3e58dd5d36e8c6a2f4780d372ec7ea590eed8804e1a3f"}