{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VLDJTS2KWXH45PY2GH5OHMYZJF","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":"50687675dbcf468192eeadcd7a9448902d69fbbad1506ff80fbb5745afb09468","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T16:20:54Z","title_canon_sha256":"9cb173a3e62d053d234522f7329d79bf98cd40a7a246ce741eddc6701ab49958"},"schema_version":"1.0","source":{"id":"2506.07905","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07905","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07905v1","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07905","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"pith_short_12","alias_value":"VLDJTS2KWXH4","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"pith_short_16","alias_value":"VLDJTS2KWXH45PY2","created_at":"2026-07-05T11:18:35Z"},{"alias_kind":"pith_short_8","alias_value":"VLDJTS2K","created_at":"2026-07-05T11:18:35Z"}],"graph_snapshots":[{"event_id":"sha256:52440ca377d2cb1c1361802f67e02bc5e5ef655c558e16ce82d1bea16eeab4b1","target":"graph","created_at":"2026-07-05T11:18:35Z","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/2506.07905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL) training paradigms to multimodal large language models (MLLM), focusing on domain-specific tasks like math and visual perception, a critical question remains: How can we achieve the general-purpose visual-language reasoning through RL? To address this challenge, we make three key efforts: (1) A novel Scalable Multimodal QA Synthesis pipeline that autonomously ge","authors_text":"Dacheng Yin, Feipeng Ma, Fengyun Rao, Jie Yang, Kang Rong, Ruimao Zhang, Zitian Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T16:20:54Z","title":"WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07905","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":"sha256:428f6a3f2ae50f036526daac5345e943c352a577f4f7d2502aaa962009626be0","target":"record","created_at":"2026-07-05T11:18:35Z","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":"50687675dbcf468192eeadcd7a9448902d69fbbad1506ff80fbb5745afb09468","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T16:20:54Z","title_canon_sha256":"9cb173a3e62d053d234522f7329d79bf98cd40a7a246ce741eddc6701ab49958"},"schema_version":"1.0","source":{"id":"2506.07905","kind":"arxiv","version":1}},"canonical_sha256":"aac699cb4ab5cfcebf1a31fae3b319497ba2f679fa27eebef15b33a891c909b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aac699cb4ab5cfcebf1a31fae3b319497ba2f679fa27eebef15b33a891c909b8","first_computed_at":"2026-07-05T11:18:35.211447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:35.211447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OrGSA83OJ1OLHD2wrhkaJlHwqmAmrA3nRBWvbUcUZAln6InIUiz9tkEZH/6yBeiXDNFY7POg7MOUMZfNY57NCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:35.211964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07905","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:428f6a3f2ae50f036526daac5345e943c352a577f4f7d2502aaa962009626be0","sha256:52440ca377d2cb1c1361802f67e02bc5e5ef655c558e16ce82d1bea16eeab4b1"],"state_sha256":"5250d1a66663a0cc1139c9768bd81a849108dfdade281cd469f21d4b0506803b"}