{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XNCSBJ22APK4F5FVUX5KVRUYNG","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":"73ab7f1cc19b4e908c66848e4e064afff9693c40cd39ac9542649f336bbb7b4a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T08:15:16Z","title_canon_sha256":"db48b9a854281ad69a1743e300220d0c8f0f3929fd89be19dde5177f41acf6e2"},"schema_version":"1.0","source":{"id":"2608.10628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10628","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10628v1","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10628","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"XNCSBJ22APK4","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"XNCSBJ22APK4F5FV","created_at":"2026-08-12T01:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"XNCSBJ22","created_at":"2026-08-12T01:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:bd1239831ac20c5fa68e3077daacb629fde80ad9a6cec3b5a7209be67ba33bcc","target":"graph","created_at":"2026-08-12T01:22:54Z","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/2608.10628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we propose InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource. InSight-doc starts from low resolution and selectively zooms into high-resolution regions for finer evidence, without relying on any external retriever. To train such an agent, we construct an active-perception corpus of 17.9K high-quality SFT examples with region-level zoom-in trajectories, accompanied by 19.2K hard ","authors_text":"Jiannan Wu, Kaican Li, Lanqing Hong, Lewei Yao, Nevin L. Zhang, Weiyan Xie, Yongxiang Huang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T08:15:16Z","title":"InSight-doc: Agentic Visual Perception for Long-Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10628","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":"sha256:6b36aa03368cb96ae2918fa2088818a3efd9e9721e4956a0426d0ba7ee34c1d7","target":"record","created_at":"2026-08-12T01:22:54Z","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":"73ab7f1cc19b4e908c66848e4e064afff9693c40cd39ac9542649f336bbb7b4a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T08:15:16Z","title_canon_sha256":"db48b9a854281ad69a1743e300220d0c8f0f3929fd89be19dde5177f41acf6e2"},"schema_version":"1.0","source":{"id":"2608.10628","kind":"arxiv","version":1}},"canonical_sha256":"bb4520a75a03d5c2f4b5a5faaac698698cc3f37367151ee7229a131e70f3b2e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb4520a75a03d5c2f4b5a5faaac698698cc3f37367151ee7229a131e70f3b2e5","first_computed_at":"2026-08-12T01:22:54.198298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:22:54.198298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2ZRwWI0Lt4p9E8WuxQGsW6Mv2Jdc7xAgj97ojbGVDauGCpIvgdizYJYI3AwNsDT0ITkPaM7xsalGRZjLo7kaAQ==","signature_status":"signed_v1","signed_at":"2026-08-12T01:22:54.199970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b36aa03368cb96ae2918fa2088818a3efd9e9721e4956a0426d0ba7ee34c1d7","sha256:bd1239831ac20c5fa68e3077daacb629fde80ad9a6cec3b5a7209be67ba33bcc"],"state_sha256":"77e60f07b47e4c7ef9190a55dff601d5709be4ffa8431c5eacc4197934d94345"}