{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NHFCSFEZVIN6IRC4DDIRI3MOUJ","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":"013c560828e343e65420b293d4555dd944a7d8a855dd1b96f5ac880ac17246ba","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T07:14:44Z","title_canon_sha256":"f29fd610c3e259c302f1b719e1bff0263e61b5f0fa3cd081e1d2280290310f91"},"schema_version":"1.0","source":{"id":"2605.17295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17295","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17295v1","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17295","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"NHFCSFEZVIN6","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"NHFCSFEZVIN6IRC4","created_at":"2026-05-20T00:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"NHFCSFEZ","created_at":"2026-05-20T00:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:e3df97994e5313068611da8f8bc8dd83c8c757fd98c068aae94a792e7ac8821f","target":"graph","created_at":"2026-05-20T00:03:50Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.809570Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.763895Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17295/integrity.json","findings":[],"snapshot_sha256":"f431f76d5be6e2c9584cd28390f2ace3c73e55d459858a30c3ce1eb442bd25f9","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern reasoning agents are increasingly evaluated on their ability to generate multiple valid solution paths, plans, or tool-use traces for a given input. Standard reward-maximizing RL tends to collapse onto the most easily reinforced high-reward mode, whereas distribution-matching RL aims to allocate probability mass across the entire reward-shaped solution set. Achieving this objective requires computing a prompt-dependent partition function over the trajectory space. Because existing distribution-matching methods learn this partition function online alongside the policy, calibration errors","authors_text":"Dayiheng Liu, Huiqiang Jiang, Linfeng Zhang, Shaobo Wang, Sihang Li, Wenjie Qiu, Xingzhang Ren, Xuming Hu, Yafeng Sun, Yucheng Li, Yujie Chen, Zhihui Xie","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T07:14:44Z","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17295","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":"sha256:99b0849af2fc5e35037931e70e4988bbe1efcce01384a626ab8716de876409af","target":"record","created_at":"2026-05-20T00:03:50Z","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":"013c560828e343e65420b293d4555dd944a7d8a855dd1b96f5ac880ac17246ba","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T07:14:44Z","title_canon_sha256":"f29fd610c3e259c302f1b719e1bff0263e61b5f0fa3cd081e1d2280290310f91"},"schema_version":"1.0","source":{"id":"2605.17295","kind":"arxiv","version":1}},"canonical_sha256":"69ca291499aa1be4445c18d1146d8ea26716fd90b8c7cc2f038b28045766b076","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69ca291499aa1be4445c18d1146d8ea26716fd90b8c7cc2f038b28045766b076","first_computed_at":"2026-05-20T00:03:50.736857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:50.736857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sR0EgWF+u52F9FbIIRzFYcMgd24PnAfG4pJc8Pofm80rI1qzu6JG4JxOlShaj8iFAqar/vWdyf3bVxZEsW/qBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:50.737758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99b0849af2fc5e35037931e70e4988bbe1efcce01384a626ab8716de876409af","sha256:e3df97994e5313068611da8f8bc8dd83c8c757fd98c068aae94a792e7ac8821f"],"state_sha256":"c87455872d9b9448e5d76e5f49ace70ee43835b49426faab14f0c8009dd6408f"}