{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SQWQORPKXMMMKL2TKBWRNGZLBE","short_pith_number":"pith:SQWQORPK","schema_version":"1.0","canonical_sha256":"942d0745eabb18c52f53506d169b2b092b47e377040a1d9fd21722cac9c930d9","source":{"kind":"arxiv","id":"2507.01951","version":2},"attestation_state":"computed","paper":{"title":"Test-Time Scaling with Reflective Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"ChenHui Jin, Guangcan Liu, Hongtao Xie, Jianjun Xu, Jie Gao, Mengting Xing, Shengzhuo Zhang, Xiaorui Wang, Yuxin Wang, Zhuo Wang, Zixiao Wang","submitted_at":"2025-07-02T17:58:01Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.01951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T17:58:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b1bb94c92162290f5672149b1a1bf22e3f5fefebd22bf3adc53d3399be28e753","abstract_canon_sha256":"62e67d43d388587b505c020d1211912f360d1524712352bbfab6a542dd03deba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:11.015920Z","signature_b64":"HMNotcVYh9/uiLEajQNYzMBxXfzEnSFFv6QMaM4aYUGubH1LKo9P/R8OvtknySvBcBFREzJYCib4ecPF81R7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"942d0745eabb18c52f53506d169b2b092b47e377040a1d9fd21722cac9c930d9","last_reissued_at":"2026-07-05T11:34:11.015453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:11.015453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time Scaling with Reflective Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"ChenHui Jin, Guangcan Liu, Hongtao Xie, Jianjun Xu, Jie Gao, Mengting Xing, Shengzhuo Zhang, Xiaorui Wang, Yuxin Wang, Zhuo Wang, Zixiao Wang","submitted_at":"2025-07-02T17:58:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01951","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.01951/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.01951","created_at":"2026-07-05T11:34:11.015510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01951v2","created_at":"2026-07-05T11:34:11.015510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01951","created_at":"2026-07-05T11:34:11.015510+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQWQORPKXMMM","created_at":"2026-07-05T11:34:11.015510+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQWQORPKXMMMKL2T","created_at":"2026-07-05T11:34:11.015510+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQWQORPK","created_at":"2026-07-05T11:34:11.015510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE","json":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE.json","graph_json":"https://pith.science/api/pith-number/SQWQORPKXMMMKL2TKBWRNGZLBE/graph.json","events_json":"https://pith.science/api/pith-number/SQWQORPKXMMMKL2TKBWRNGZLBE/events.json","paper":"https://pith.science/paper/SQWQORPK"},"agent_actions":{"view_html":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE","download_json":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE.json","view_paper":"https://pith.science/paper/SQWQORPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01951&json=true","fetch_graph":"https://pith.science/api/pith-number/SQWQORPKXMMMKL2TKBWRNGZLBE/graph.json","fetch_events":"https://pith.science/api/pith-number/SQWQORPKXMMMKL2TKBWRNGZLBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE/action/storage_attestation","attest_author":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE/action/author_attestation","sign_citation":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE/action/citation_signature","submit_replication":"https://pith.science/pith/SQWQORPKXMMMKL2TKBWRNGZLBE/action/replication_record"}},"created_at":"2026-07-05T11:34:11.015510+00:00","updated_at":"2026-07-05T11:34:11.015510+00:00"}