{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LWNQYQRP5FO7FWQKIWBZRBTRNK","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":"b4bdca8e408ae9de923a6624d368f022ff58465a5093e87fa53fe942d1dec91b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-04T02:41:04Z","title_canon_sha256":"db82532ddd50b0ba9d6b121d70296cd5bd38dcba15676993f99cbab9add86189"},"schema_version":"1.0","source":{"id":"2409.02392","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02392","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02392v2","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02392","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"LWNQYQRP5FO7","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"LWNQYQRP5FO7FWQK","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"LWNQYQRP","created_at":"2026-07-05T10:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:f491124f77ac1cd6143379dea296fc415ea0225edd93f8f0053cd2e26bcc8ed8","target":"graph","created_at":"2026-07-05T10:21:22Z","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/2409.02392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have shown that large language models' (LLMs) mathematical problem-solving capabilities can be enhanced by integrating external tools, such as code interpreters, and employing multi-turn Chain-of-Thought (CoT) reasoning. While current methods focus on synthetic data generation and Supervised Fine-Tuning (SFT), this paper studies the complementary direct preference learning approach to further improve model performance. However, existing direct preference learning algorithms are originally designed for the single-turn chat task, and do not fully address the complexities of multi-","authors_text":"Aviv Rosenberg, Bilal Piot, Chengshuai Shi, Chi Jin, Daniele Calandriello, Jiaming Shen, Misha Khalman, Mohammad Saleh, Rishabh Joshi, Tianqi Liu, Tong Zhang, Wei Xiong, Zhen Qin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-04T02:41:04Z","title":"Building Math Agents with Multi-Turn Iterative Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02392","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":"sha256:9662b25e489e86d1c7d55a205ad580cf5f9f0aab52bbc257bf1d108e3727f8a0","target":"record","created_at":"2026-07-05T10:21:22Z","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":"b4bdca8e408ae9de923a6624d368f022ff58465a5093e87fa53fe942d1dec91b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-04T02:41:04Z","title_canon_sha256":"db82532ddd50b0ba9d6b121d70296cd5bd38dcba15676993f99cbab9add86189"},"schema_version":"1.0","source":{"id":"2409.02392","kind":"arxiv","version":2}},"canonical_sha256":"5d9b0c422fe95df2da0a45839886716aa078564ca3f2a8dfba1eeb8c25066df9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d9b0c422fe95df2da0a45839886716aa078564ca3f2a8dfba1eeb8c25066df9","first_computed_at":"2026-07-05T10:21:22.809078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:22.809078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+uuigc9f34znzyaqGAqqKeITCaEjrYC2ybcQnfIfZpdOwMBgWASwJ0uZVJAK96O2LsFpwiMVZKkTtaf2o4xHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:22.809885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02392","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9662b25e489e86d1c7d55a205ad580cf5f9f0aab52bbc257bf1d108e3727f8a0","sha256:f491124f77ac1cd6143379dea296fc415ea0225edd93f8f0053cd2e26bcc8ed8"],"state_sha256":"4804d03c29cef480aa46a9c03e12aca7f685383638c926337fd6a63bba3bb58d"}