{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YQMUAHGAEMTDSGPZNMAB4SJUYL","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":"64435704e286deb5c89dc8ec292a9c9026b42a5e3b369fb3bfa833b472dca408","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:45:16Z","title_canon_sha256":"96f1199076d33bfa8c2415b831a0db03d5b10205a08ccfea5c82a0436af90f3d"},"schema_version":"1.0","source":{"id":"2506.02096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02096","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02096v1","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02096","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"YQMUAHGAEMTD","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"YQMUAHGAEMTDSGPZ","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"YQMUAHGA","created_at":"2026-07-05T11:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:7b034150b1bd0e687d791129fb59f26e7529ddb4661f0a9a589de4d09fb15ce2","target":"graph","created_at":"2026-07-05T11:14:32Z","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/2506.02096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively. In this work, we investigate how synthesized RL data can further improve RLVR. To this end, we propose \\textbf{SynthRL}-a scalable and guaranteed pipeline for automatic data scaling in reasoning-oriented RL training. SynthRL comprises three key stages: (1) selecting seed questions with appropriate distribution, (2) augmenting them into more challenging variants while preserving the original answers, and (3) a guaranteed verificatio","authors_text":"Hang Yan, Jinjie Ni, Michael Qizhe Shieh, Xiangyan Liu, Zichen Liu, Zijian Wu","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:45:16Z","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02096","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":"sha256:84b34121bc1e8b43a7c369f0847cf7b367397d21a52c4830ddd91e74c17fa809","target":"record","created_at":"2026-07-05T11:14:32Z","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":"64435704e286deb5c89dc8ec292a9c9026b42a5e3b369fb3bfa833b472dca408","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:45:16Z","title_canon_sha256":"96f1199076d33bfa8c2415b831a0db03d5b10205a08ccfea5c82a0436af90f3d"},"schema_version":"1.0","source":{"id":"2506.02096","kind":"arxiv","version":1}},"canonical_sha256":"c419401cc023263919f96b001e4934c2ef804490c66fb43ff6ff1640d12d09fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c419401cc023263919f96b001e4934c2ef804490c66fb43ff6ff1640d12d09fd","first_computed_at":"2026-07-05T11:14:32.340207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:32.340207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4aoNc1Uc4GspGlRFeleKoUOD0WP8TtFjPUPXuTWqmRY6yUcJYJJFUAaObfTrUScfe9uasS1bRUGqRNXN3bkOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:32.340669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84b34121bc1e8b43a7c369f0847cf7b367397d21a52c4830ddd91e74c17fa809","sha256:7b034150b1bd0e687d791129fb59f26e7529ddb4661f0a9a589de4d09fb15ce2"],"state_sha256":"2b4276fd1de7c8dcfc8dd61c7037da81eb000be78186081c6bb1401b6d7f41b7"}