{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LNFL2OAK2WLIILCVMGLQHN4W6B","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":"d9dde23142a3aaf8245ea33b56a9fece187651f17f68d9f4130492cb0f083b62","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T09:20:04Z","title_canon_sha256":"d7b3ffa534d8199babb62128800f9e8b0cda80b6227e3fb1e602cb99c56f488d"},"schema_version":"1.0","source":{"id":"2509.06461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06461","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06461v2","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06461","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"LNFL2OAK2WLI","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"LNFL2OAK2WLIILCV","created_at":"2026-07-05T12:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"LNFL2OAK","created_at":"2026-07-05T12:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:585e678eeadef2f4540c55f817df15777df1172082e24e4ecf0101153f6bd817","target":"graph","created_at":"2026-07-05T12:09:24Z","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/2509.06461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visual environments. While existing enhancement approaches require additional training, rely on external segmentation tools, or operate at coarse-grained levels, they overlook the innate ability within VLMs. To bridge this gap, we investigate VLMs' attention patterns and discover that: (1) visual complexity strongly correlates with attention entropy, negatively impacting reasoning performance; (2) attention progressively refines from global scanning in shall","authors_text":"Baolong Bi, Jiafeng Guo, Jiayu Yao, Lingrui Mei, Shenghua Liu, Xuanshan Zhou, Xueqi Cheng, Yiwei Wang, Yuyao Ge","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T09:20:04Z","title":"Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06461","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":"sha256:80b95cf7ac93828d49cd4c626838e7677cd7563abbe6fe2509b9395fcf910de4","target":"record","created_at":"2026-07-05T12:09:24Z","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":"d9dde23142a3aaf8245ea33b56a9fece187651f17f68d9f4130492cb0f083b62","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T09:20:04Z","title_canon_sha256":"d7b3ffa534d8199babb62128800f9e8b0cda80b6227e3fb1e602cb99c56f488d"},"schema_version":"1.0","source":{"id":"2509.06461","kind":"arxiv","version":2}},"canonical_sha256":"5b4abd380ad596842c55619703b796f04a7836895b32f8e9a4d3bd1c02d8eeca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b4abd380ad596842c55619703b796f04a7836895b32f8e9a4d3bd1c02d8eeca","first_computed_at":"2026-07-05T12:09:24.211498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:24.211498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/FoCtjBBTCQK1ybIjc8aVEoafdoZ050sqBU9FDgU4o+NBQuBea8a1smeSauSSk9OlTOMTtL28MDm6cI/y3mmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:24.211975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80b95cf7ac93828d49cd4c626838e7677cd7563abbe6fe2509b9395fcf910de4","sha256:585e678eeadef2f4540c55f817df15777df1172082e24e4ecf0101153f6bd817"],"state_sha256":"b991309909d8a7b60169c3f2603aa05546058b76a1cb4736143e7ae57fb6e241"}