{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HVFBBWE6ZBYPLBIYA5ZAP4SU4G","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":"16e46010ed7b3313fb18d263658c2e1f99f004f73883dc69974170db126f3c82","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T04:33:41Z","title_canon_sha256":"6535eb16ed9a13195a5237edf3844982feaf2c5fe669d5da45480b4802bc1899"},"schema_version":"1.0","source":{"id":"2505.18499","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18499","created_at":"2026-07-05T11:55:40Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18499v3","created_at":"2026-07-05T11:55:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18499","created_at":"2026-07-05T11:55:40Z"},{"alias_kind":"pith_short_12","alias_value":"HVFBBWE6ZBYP","created_at":"2026-07-05T11:55:40Z"},{"alias_kind":"pith_short_16","alias_value":"HVFBBWE6ZBYPLBIY","created_at":"2026-07-05T11:55:40Z"},{"alias_kind":"pith_short_8","alias_value":"HVFBBWE6","created_at":"2026-07-05T11:55:40Z"}],"graph_snapshots":[{"event_id":"sha256:1645a440f9a7cc79c417f68495b0d6d40ecaed9087de8dbebe1d1ac12bbbbe40","target":"graph","created_at":"2026-07-05T11:55:40Z","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/2505.18499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Large Language Models (LLMs) have demonstrated remarkable progress, their proficiency in graph-related tasks remains notably limited, hindering the development of truly general-purpose models. Previous attempts, including pretraining graph foundation models or employing supervised fine-tuning, often face challenges such as the scarcity of large-scale, universally represented graph data. We introduce G1, a simple yet effective approach demonstrating that Reinforcement Learning (RL) on synthetic graph-theoretic tasks can significantly scale LLMs' graph reasoning abilities. To enable RL ","authors_text":"Ang Li, Stefanie Jegelka, Xiaojun Guo, Yifei Wang, Yisen Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T04:33:41Z","title":"G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18499","kind":"arxiv","version":3},"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":"sha256:30d10fd046c883e339ad4ee4b2f4a758fdd249bed4517853bf68741a8ca7887e","target":"record","created_at":"2026-07-05T11:55:40Z","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":"16e46010ed7b3313fb18d263658c2e1f99f004f73883dc69974170db126f3c82","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T04:33:41Z","title_canon_sha256":"6535eb16ed9a13195a5237edf3844982feaf2c5fe669d5da45480b4802bc1899"},"schema_version":"1.0","source":{"id":"2505.18499","kind":"arxiv","version":3}},"canonical_sha256":"3d4a10d89ec870f58518077207f254e19c48c3dd344e645319749e5b104a1930","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d4a10d89ec870f58518077207f254e19c48c3dd344e645319749e5b104a1930","first_computed_at":"2026-07-05T11:55:40.151487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:40.151487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3SsKwuuunujtnA+VcvM8tzPAi40+pBoYzhBmWNWozRRCdb+xSuhCk/SzoM1VzQ/zkJiJQIynnkjYFnJJieTtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:40.151934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18499","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30d10fd046c883e339ad4ee4b2f4a758fdd249bed4517853bf68741a8ca7887e","sha256:1645a440f9a7cc79c417f68495b0d6d40ecaed9087de8dbebe1d1ac12bbbbe40"],"state_sha256":"14d4ac615ef0b4185d30344a6f4ad840d08882c0a93ccad1c1c68cb0f8dc40e7"}