{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SQWQORPKXMMMKL2TKBWRNGZLBE","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":"62e67d43d388587b505c020d1211912f360d1524712352bbfab6a542dd03deba","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T17:58:01Z","title_canon_sha256":"b1bb94c92162290f5672149b1a1bf22e3f5fefebd22bf3adc53d3399be28e753"},"schema_version":"1.0","source":{"id":"2507.01951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01951","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01951v2","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01951","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"SQWQORPKXMMM","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"SQWQORPKXMMMKL2T","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"SQWQORPK","created_at":"2026-07-05T11:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:3c7e9539caefe509bff55233c7f73384749a8a1a49efd8eafc54892c9f52e246","target":"graph","created_at":"2026-07-05T11:34:11Z","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/2507.01951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce our first reflective generative model MetaStone-S1, which obtains OpenAI o3-mini's performance via the new Reflective Generative Form. The new form focuses on high-quality reasoning trajectory selection and contains two novelties: 1) A unified interface for policy and process reward model: we share the backbone network and use task-specific heads for reasoning trajectory predicting and scoring respectively, introducing only 53M extra parameters for trajectory scoring. 2) Eliminating the reliance on process-level annotation: we provide a self-supervised process reward model, which ","authors_text":"ChenHui Jin, Guangcan Liu, Hongtao Xie, Jianjun Xu, Jie Gao, Mengting Xing, Shengzhuo Zhang, Xiaorui Wang, Yuxin Wang, Zhuo Wang, Zixiao Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T17:58:01Z","title":"Test-Time Scaling with Reflective Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01951","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":"sha256:9640425ca86670b6842178e59636eaed7b76bd4d4fc15495e5fe53b302691ff6","target":"record","created_at":"2026-07-05T11:34:11Z","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":"62e67d43d388587b505c020d1211912f360d1524712352bbfab6a542dd03deba","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T17:58:01Z","title_canon_sha256":"b1bb94c92162290f5672149b1a1bf22e3f5fefebd22bf3adc53d3399be28e753"},"schema_version":"1.0","source":{"id":"2507.01951","kind":"arxiv","version":2}},"canonical_sha256":"942d0745eabb18c52f53506d169b2b092b47e377040a1d9fd21722cac9c930d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"942d0745eabb18c52f53506d169b2b092b47e377040a1d9fd21722cac9c930d9","first_computed_at":"2026-07-05T11:34:11.015453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:11.015453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HMNotcVYh9/uiLEajQNYzMBxXfzEnSFFv6QMaM4aYUGubH1LKo9P/R8OvtknySvBcBFREzJYCib4ecPF81R7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:11.015920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9640425ca86670b6842178e59636eaed7b76bd4d4fc15495e5fe53b302691ff6","sha256:3c7e9539caefe509bff55233c7f73384749a8a1a49efd8eafc54892c9f52e246"],"state_sha256":"dfb86428af8c9617d01c9d6b1e92b86f89b0faf3b6c0b7dae7f633c22e17eb9a"}