{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YIUONH5QMKFGRDSHLXT4CSFTFZ","short_pith_number":"pith:YIUONH5Q","schema_version":"1.0","canonical_sha256":"c228e69fb0628a688e475de7c148b32e5eeef7e19f530fcd6e7ea8baa496dd31","source":{"kind":"arxiv","id":"2606.20515","version":1},"attestation_state":"computed","paper":{"title":"S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoliang Tian, Dingwen Zhang, Fangfu Liu, Fangzhou Hong, Hao Li, Kim-Hui Yap, Runmao Yao, Shulin Tian, Tao Wang, Yalun Dai, Yuhao Dong, Zhaoxi Chen, Ziwei Liu","submitted_at":"2026-06-18T17:34:55Z","abstract_excerpt":"Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inference from isolated visual observations. We introduce \\textbf{\\textsc{S-Agent}}, a spatial tool-use agentic paradigm for understanding and reasoning over continuous multi-view images and videos. By formulating spatial reasoning as spatio-temporal evidence accumulation rather than isolated frame-level prediction, \\textsc{S-Agent} reshapes spatial perception into scene-centric understanding beyond frame-centric recogn"},"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":"2606.20515","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T17:34:55Z","cross_cats_sorted":[],"title_canon_sha256":"0599739ab7cbde28814ace177ec5afee6fcbd855439a6160c493af184cb10283","abstract_canon_sha256":"cd4c4c00d79d40fde177b9666fc2829d0f66ec1deb346bc6046a5488809ac828"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:14.229500Z","signature_b64":"6bQlLGE3SjGOeIEEVhVfEF9VvzBFt9xih3eW+ODKi/pNkGVeOVE8YLE+356+NTRskXmloZE6Q4VRBl19qKCVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c228e69fb0628a688e475de7c148b32e5eeef7e19f530fcd6e7ea8baa496dd31","last_reissued_at":"2026-06-19T16:13:14.229131Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:14.229131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoliang Tian, Dingwen Zhang, Fangfu Liu, Fangzhou Hong, Hao Li, Kim-Hui Yap, Runmao Yao, Shulin Tian, Tao Wang, Yalun Dai, Yuhao Dong, Zhaoxi Chen, Ziwei Liu","submitted_at":"2026-06-18T17:34:55Z","abstract_excerpt":"Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inference from isolated visual observations. We introduce \\textbf{\\textsc{S-Agent}}, a spatial tool-use agentic paradigm for understanding and reasoning over continuous multi-view images and videos. By formulating spatial reasoning as spatio-temporal evidence accumulation rather than isolated frame-level prediction, \\textsc{S-Agent} reshapes spatial perception into scene-centric understanding beyond frame-centric recogn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20515","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/2606.20515/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":"2606.20515","created_at":"2026-06-19T16:13:14.229195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20515v1","created_at":"2026-06-19T16:13:14.229195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20515","created_at":"2026-06-19T16:13:14.229195+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIUONH5QMKFG","created_at":"2026-06-19T16:13:14.229195+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIUONH5QMKFGRDSH","created_at":"2026-06-19T16:13:14.229195+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIUONH5Q","created_at":"2026-06-19T16:13:14.229195+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/YIUONH5QMKFGRDSHLXT4CSFTFZ","json":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ.json","graph_json":"https://pith.science/api/pith-number/YIUONH5QMKFGRDSHLXT4CSFTFZ/graph.json","events_json":"https://pith.science/api/pith-number/YIUONH5QMKFGRDSHLXT4CSFTFZ/events.json","paper":"https://pith.science/paper/YIUONH5Q"},"agent_actions":{"view_html":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ","download_json":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ.json","view_paper":"https://pith.science/paper/YIUONH5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20515&json=true","fetch_graph":"https://pith.science/api/pith-number/YIUONH5QMKFGRDSHLXT4CSFTFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YIUONH5QMKFGRDSHLXT4CSFTFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ/action/storage_attestation","attest_author":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ/action/author_attestation","sign_citation":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ/action/citation_signature","submit_replication":"https://pith.science/pith/YIUONH5QMKFGRDSHLXT4CSFTFZ/action/replication_record"}},"created_at":"2026-06-19T16:13:14.229195+00:00","updated_at":"2026-06-19T16:13:14.229195+00:00"}