{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:53TYEFSTFJHLDAABUDJSVLABDY","short_pith_number":"pith:53TYEFST","schema_version":"1.0","canonical_sha256":"eee78216532a4eb18001a0d32aac011e0800bdbb04987b3b64a37c4acfe348f1","source":{"kind":"arxiv","id":"2606.12830","version":1},"attestation_state":"computed","paper":{"title":"Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changye Li, Ligeng Zhu, Meng Lu, Yi Wu","submitted_at":"2026-06-11T02:54:07Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.12830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T02:54:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1a00fde359d386eec4156667dcf532be6901085e2467cb5b7093774323f2d57","abstract_canon_sha256":"879d79cf1136f1298431ac997a4746bdd2492b05808f1e5c4495747e3a6a449a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:53.130013Z","signature_b64":"v1iQhFsPbjYHStLotULeRMrCVXtPLW7lo4WFzRQITnlyjOD4J5Ho1Ky5+YRytU48ITpQo7DOKZVp/jRoDoukCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eee78216532a4eb18001a0d32aac011e0800bdbb04987b3b64a37c4acfe348f1","last_reissued_at":"2026-06-12T01:08:53.129292Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:53.129292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changye Li, Ligeng Zhu, Meng Lu, Yi Wu","submitted_at":"2026-06-11T02:54:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12830","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.12830/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.12830","created_at":"2026-06-12T01:08:53.129419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12830v1","created_at":"2026-06-12T01:08:53.129419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12830","created_at":"2026-06-12T01:08:53.129419+00:00"},{"alias_kind":"pith_short_12","alias_value":"53TYEFSTFJHL","created_at":"2026-06-12T01:08:53.129419+00:00"},{"alias_kind":"pith_short_16","alias_value":"53TYEFSTFJHLDAAB","created_at":"2026-06-12T01:08:53.129419+00:00"},{"alias_kind":"pith_short_8","alias_value":"53TYEFST","created_at":"2026-06-12T01:08:53.129419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY","json":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY.json","graph_json":"https://pith.science/api/pith-number/53TYEFSTFJHLDAABUDJSVLABDY/graph.json","events_json":"https://pith.science/api/pith-number/53TYEFSTFJHLDAABUDJSVLABDY/events.json","paper":"https://pith.science/paper/53TYEFST"},"agent_actions":{"view_html":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY","download_json":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY.json","view_paper":"https://pith.science/paper/53TYEFST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12830&json=true","fetch_graph":"https://pith.science/api/pith-number/53TYEFSTFJHLDAABUDJSVLABDY/graph.json","fetch_events":"https://pith.science/api/pith-number/53TYEFSTFJHLDAABUDJSVLABDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY/action/storage_attestation","attest_author":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY/action/author_attestation","sign_citation":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY/action/citation_signature","submit_replication":"https://pith.science/pith/53TYEFSTFJHLDAABUDJSVLABDY/action/replication_record"}},"created_at":"2026-06-12T01:08:53.129419+00:00","updated_at":"2026-06-12T01:08:53.129419+00:00"}