{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:53TYEFSTFJHLDAABUDJSVLABDY","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":"879d79cf1136f1298431ac997a4746bdd2492b05808f1e5c4495747e3a6a449a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T02:54:07Z","title_canon_sha256":"b1a00fde359d386eec4156667dcf532be6901085e2467cb5b7093774323f2d57"},"schema_version":"1.0","source":{"id":"2606.12830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12830","created_at":"2026-06-12T01:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12830v1","created_at":"2026-06-12T01:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12830","created_at":"2026-06-12T01:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"53TYEFSTFJHL","created_at":"2026-06-12T01:08:53Z"},{"alias_kind":"pith_short_16","alias_value":"53TYEFSTFJHLDAAB","created_at":"2026-06-12T01:08:53Z"},{"alias_kind":"pith_short_8","alias_value":"53TYEFST","created_at":"2026-06-12T01:08:53Z"}],"graph_snapshots":[{"event_id":"sha256:973981bb0d120c9eaa4c4b10426b5a87b997887554626c5cfb11dd70a2a7d8ac","target":"graph","created_at":"2026-06-12T01:08:53Z","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/2606.12830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction. This limitation suggests that relying solely on implicit visual representations from vision encoders is insufficient for recovering fine-grained spatial evidence. We introduce PERception-Interaction-reason Agent (PERIA), a tool-augmented visual agent for spatial reasoning tasks across map reasoning, visual probing, and vision reconstruction. PERIA uses two lightweight tool families: vis","authors_text":"Changye Li, Ligeng Zhu, Meng Lu, Yi Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T02:54:07Z","title":"Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12830","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":"sha256:93d98c3352ece618376a4fb93a4fc96fc43996a2c047713f4012148df0b3d447","target":"record","created_at":"2026-06-12T01:08:53Z","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":"879d79cf1136f1298431ac997a4746bdd2492b05808f1e5c4495747e3a6a449a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T02:54:07Z","title_canon_sha256":"b1a00fde359d386eec4156667dcf532be6901085e2467cb5b7093774323f2d57"},"schema_version":"1.0","source":{"id":"2606.12830","kind":"arxiv","version":1}},"canonical_sha256":"eee78216532a4eb18001a0d32aac011e0800bdbb04987b3b64a37c4acfe348f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eee78216532a4eb18001a0d32aac011e0800bdbb04987b3b64a37c4acfe348f1","first_computed_at":"2026-06-12T01:08:53.129292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:53.129292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v1iQhFsPbjYHStLotULeRMrCVXtPLW7lo4WFzRQITnlyjOD4J5Ho1Ky5+YRytU48ITpQo7DOKZVp/jRoDoukCQ==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:53.130013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93d98c3352ece618376a4fb93a4fc96fc43996a2c047713f4012148df0b3d447","sha256:973981bb0d120c9eaa4c4b10426b5a87b997887554626c5cfb11dd70a2a7d8ac"],"state_sha256":"78d793707e5bf12d690688cb44d81c4df962597c953f094f336d87dd98536d4d"}