{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EXBDWUR7HA7VZ62ERKEZS5IS4F","short_pith_number":"pith:EXBDWUR7","schema_version":"1.0","canonical_sha256":"25c23b523f383f5cfb448a89997512e14d846dbcbe45fce763da5985596b1fad","source":{"kind":"arxiv","id":"2606.13673","version":1},"attestation_state":"computed","paper":{"title":"SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhishek Badki, Byung-Kwan Lee, Chan Hee Song, Hang Su, Min-Hung Chen, Ryo Hachiuma, Seokju Cho, Seungryong Kim, Sifei Liu, Subhashree Radhakrishnan, Yu-Chiang Frank Wang","submitted_at":"2026-06-11T17:59:36Z","abstract_excerpt":"Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by augmenting VLMs with specialist perception modules, yet their effectiveness is bounded by the action interface through which those tools are invoked. In this work, we study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning. Existing spatial agents either employ single-pass code execution, which commits to a full analysis strategy bef"},"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":"2606.13673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T17:59:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a382226beb30a4da468ec990d451b850f5d799c2ad8dc5362c142c9294434ee","abstract_canon_sha256":"b386c06ec7faac2552c55b05b385497c31fb898fa61fcb7bd1f30fdf46c10682"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:22.747012Z","signature_b64":"EvTxHkhZyxemehnqy0tjlrm+RR5lupBxd1zh8Cf3R/VSVv5sM3pzESVJwTIZICWfi5LghwT21U+dE022dygZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25c23b523f383f5cfb448a89997512e14d846dbcbe45fce763da5985596b1fad","last_reissued_at":"2026-06-12T01:10:22.746139Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:22.746139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhishek Badki, Byung-Kwan Lee, Chan Hee Song, Hang Su, Min-Hung Chen, Ryo Hachiuma, Seokju Cho, Seungryong Kim, Sifei Liu, Subhashree Radhakrishnan, Yu-Chiang Frank Wang","submitted_at":"2026-06-11T17:59:36Z","abstract_excerpt":"Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by augmenting VLMs with specialist perception modules, yet their effectiveness is bounded by the action interface through which those tools are invoked. In this work, we study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning. Existing spatial agents either employ single-pass code execution, which commits to a full analysis strategy bef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13673","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/2606.13673/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":"2606.13673","created_at":"2026-06-12T01:10:22.746276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13673v1","created_at":"2026-06-12T01:10:22.746276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13673","created_at":"2026-06-12T01:10:22.746276+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXBDWUR7HA7V","created_at":"2026-06-12T01:10:22.746276+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXBDWUR7HA7VZ62E","created_at":"2026-06-12T01:10:22.746276+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXBDWUR7","created_at":"2026-06-12T01:10:22.746276+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/EXBDWUR7HA7VZ62ERKEZS5IS4F","json":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F.json","graph_json":"https://pith.science/api/pith-number/EXBDWUR7HA7VZ62ERKEZS5IS4F/graph.json","events_json":"https://pith.science/api/pith-number/EXBDWUR7HA7VZ62ERKEZS5IS4F/events.json","paper":"https://pith.science/paper/EXBDWUR7"},"agent_actions":{"view_html":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F","download_json":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F.json","view_paper":"https://pith.science/paper/EXBDWUR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13673&json=true","fetch_graph":"https://pith.science/api/pith-number/EXBDWUR7HA7VZ62ERKEZS5IS4F/graph.json","fetch_events":"https://pith.science/api/pith-number/EXBDWUR7HA7VZ62ERKEZS5IS4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F/action/storage_attestation","attest_author":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F/action/author_attestation","sign_citation":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F/action/citation_signature","submit_replication":"https://pith.science/pith/EXBDWUR7HA7VZ62ERKEZS5IS4F/action/replication_record"}},"created_at":"2026-06-12T01:10:22.746276+00:00","updated_at":"2026-06-12T01:10:22.746276+00:00"}