{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IQGIMFN2WN372YFSB3KPHI72SK","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":"d05252881397b6f611c8db3e349b6578698a5fb54deab99a2fab751ba75a1305","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T20:11:44Z","title_canon_sha256":"03d84ab0a2d362b345b34d83308e9ba082caf1994ad02db5254a7eddd636def9"},"schema_version":"1.0","source":{"id":"2506.14821","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14821","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14821v3","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14821","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"IQGIMFN2WN37","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"IQGIMFN2WN372YFS","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"IQGIMFN2","created_at":"2026-07-05T11:48:26Z"}],"graph_snapshots":[{"event_id":"sha256:123a4437cce2abbcb7b8ed59d2dc5fad79244366fde7034b3bd6484dbb5564c6","target":"graph","created_at":"2026-07-05T11:48:26Z","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/2506.14821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite tremendous recent advances in large model reasoning ability, vision-language models (VLMs) still struggle with detailed visual reasoning, especially when compute resources are limited. To address this challenge, we draw inspiration from methods like Deepseek-r1 for VLMs and train smaller-scale models with Group Relative Policy Optimization (GRPO) to use external tools such as zoom. The greatest benefit is obtained with a combination of GRPO learning, a simple reward structure, a simplified tool-calling interface, allocating additional tokens to the result of the tool call, and a traini","authors_text":"Bowen Zhao, Leo Dirac, Paulina Varshavskaya, Sunil Kumar","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T20:11:44Z","title":"Reinforcing VLMs to Use Tools for Detailed Visual Reasoning Under Resource Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14821","kind":"arxiv","version":3},"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":"sha256:084df879be8148b4fea4ade32eb36094c5135b5977d6bbfad568850f9ab8c7ec","target":"record","created_at":"2026-07-05T11:48:26Z","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":"d05252881397b6f611c8db3e349b6578698a5fb54deab99a2fab751ba75a1305","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T20:11:44Z","title_canon_sha256":"03d84ab0a2d362b345b34d83308e9ba082caf1994ad02db5254a7eddd636def9"},"schema_version":"1.0","source":{"id":"2506.14821","kind":"arxiv","version":3}},"canonical_sha256":"440c8615bab377fd60b20ed4f3a3fa928c8ae3de34bf15539c03d3a5154387a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"440c8615bab377fd60b20ed4f3a3fa928c8ae3de34bf15539c03d3a5154387a6","first_computed_at":"2026-07-05T11:48:26.770799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:26.770799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iu2cFViy2A6s9Uge8nCFQnQASDhWufL4LFqM0mQW4s88kYMpzgtHeLnjpyCon0ePNJCAbejEtigYRWOR2ORLBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:26.771279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14821","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:084df879be8148b4fea4ade32eb36094c5135b5977d6bbfad568850f9ab8c7ec","sha256:123a4437cce2abbcb7b8ed59d2dc5fad79244366fde7034b3bd6484dbb5564c6"],"state_sha256":"9673d9a880f54af6b9ba46b2a2d65ce65dcc53f9dd7eb6f208e3fa3b2d42e97e"}