{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EDAYKDBTHYUQ2M37C7FDUVOP5M","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":"e259c6241bf647a20d04d92da7674952f7e4a0924344875ab7b9254b50c8b755","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-03T18:50:04Z","title_canon_sha256":"f3beab68b898a795db115a013b006647170adf2ee8b3c5caa6e00e72dd95c08b"},"schema_version":"1.0","source":{"id":"2512.04069","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.04069","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2512.04069v2","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.04069","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"EDAYKDBTHYUQ","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"EDAYKDBTHYUQ2M37","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"EDAYKDBT","created_at":"2026-06-02T03:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:22ffce1bb31c74787a9e9cd6a6d3746cd9bf9b0398cac4d01afe0da5896a0f1d","target":"graph","created_at":"2026-06-02T03:05:04Z","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/2512.04069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied applications. The agentic paradigm promises that VLMs can use a wide variety of tools that could augment these capabilities, such as depth estimators, segmentation models, and pose estimators. Yet it remains an open challenge how to realize this vision without solely relying on handcrafted prompting strategies or enforcing fixed, predefined tool pipelines that limit VLMs' ability to discover optimal tool-use patterns. Reinforcement Lear","authors_text":"Adithyavairavan Murali, Chan Hee Song, Faisal Ladhak, Jonathan Tremblay, Mikaela Angelina Uy, Qing Qu, Siyi Chen, Stan Birchfield, Valts Blukis","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-03T18:50:04Z","title":"SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.04069","kind":"arxiv","version":2},"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":"sha256:68e3dbba801a81a4ad4a1624da6dbf55a36c388a58b89c29107d6b5ecc28ad4a","target":"record","created_at":"2026-06-02T03:05:04Z","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":"e259c6241bf647a20d04d92da7674952f7e4a0924344875ab7b9254b50c8b755","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-03T18:50:04Z","title_canon_sha256":"f3beab68b898a795db115a013b006647170adf2ee8b3c5caa6e00e72dd95c08b"},"schema_version":"1.0","source":{"id":"2512.04069","kind":"arxiv","version":2}},"canonical_sha256":"20c1850c333e290d337f17ca3a55cfeb3563fe85b93965db052621102dc8f643","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20c1850c333e290d337f17ca3a55cfeb3563fe85b93965db052621102dc8f643","first_computed_at":"2026-06-02T03:05:04.407421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:05:04.407421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s1F5cKRnn3DVRDGHx9vOsQkZqgjE5PqDLah88zuPZUqGl8ucm440RP+5UL9+gSgIRdmoqU4MapjSyK/TjXNTCA==","signature_status":"signed_v1","signed_at":"2026-06-02T03:05:04.407920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.04069","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68e3dbba801a81a4ad4a1624da6dbf55a36c388a58b89c29107d6b5ecc28ad4a","sha256:22ffce1bb31c74787a9e9cd6a6d3746cd9bf9b0398cac4d01afe0da5896a0f1d"],"state_sha256":"48ba55bc8f9cf088f0f1d48f4ca56ac5872f51a3b8d697d1d9d557597ee4f42c"}