{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XKUS2V6K7DUZV3QYDDTWN7NF55","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":"1ee1f2eb30885cb1ddded5e67f65327cc473fe18276c722ec9a18e3008a080ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:54:39Z","title_canon_sha256":"5fcf76951319546f70ae635776896969c90e784e2b153856d6d06e1234129005"},"schema_version":"1.0","source":{"id":"2505.13426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13426","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13426v1","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13426","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"XKUS2V6K7DUZ","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"XKUS2V6K7DUZV3QY","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"XKUS2V6K","created_at":"2026-07-05T11:05:30Z"}],"graph_snapshots":[{"event_id":"sha256:8a9ab13b06f9d737d8a81ce7bf9c4f4e54163461de8869fe04ef6616632620ab","target":"graph","created_at":"2026-07-05T11:05:30Z","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/2505.13426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) excel in many direct multimodal tasks but struggle to translate this prowess into effective decision-making within interactive, visually rich environments like games. This ``knowing-doing'' gap significantly limits their potential as autonomous agents, as leading VLMs often performing badly in simple games. To address this, we introduce VLM-Gym, a curated reinforcement learning (RL) environment featuring diverse visual games with unified interfaces and adjustable, compositional difficulty, specifically designed for scalable multi-game parallel training. Leveraging","authors_text":"Baobao Chang, Flood Sung, Hongcheng Gao, Liang Chen, Tianyu Liu, Xinyu Zhou, Yuxin Wu, Zhiqi Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:54:39Z","title":"G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13426","kind":"arxiv","version":1},"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":"sha256:1807e108a86d9e8fff2cb29ae39f73e314e95731b0cc8dcdd6fc22ac76ca2794","target":"record","created_at":"2026-07-05T11:05:30Z","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":"1ee1f2eb30885cb1ddded5e67f65327cc473fe18276c722ec9a18e3008a080ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:54:39Z","title_canon_sha256":"5fcf76951319546f70ae635776896969c90e784e2b153856d6d06e1234129005"},"schema_version":"1.0","source":{"id":"2505.13426","kind":"arxiv","version":1}},"canonical_sha256":"baa92d57caf8e99aee1818e766fda5ef5b09c81a10cb00f32dfc5959ca3e1587","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baa92d57caf8e99aee1818e766fda5ef5b09c81a10cb00f32dfc5959ca3e1587","first_computed_at":"2026-07-05T11:05:30.020608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:30.020608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Am9ZNXw7D9PXjVnlVxoSFDAuj8wrQR8Zr0nKU3O/fozP6kuC0TWKsLH3N4tFlJvwi7ImX88EsmWBo83y1dTkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:30.021080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1807e108a86d9e8fff2cb29ae39f73e314e95731b0cc8dcdd6fc22ac76ca2794","sha256:8a9ab13b06f9d737d8a81ce7bf9c4f4e54163461de8869fe04ef6616632620ab"],"state_sha256":"167ac19138fd7dc7b73a5d4c338e364eaa8283a729ce10c840c0eb3e33656b49"}