{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NHEN6SE7X65ANL2GFQXFHMXPSK","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":"a6cf1391a1b317dcf4f8615fa7e21ee92ac4b063e1d31f89f2d9ff0079a5e9b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T11:41:46Z","title_canon_sha256":"7d53321fafee852abfe8802b30ac2e777719168c068f2c6918b7090cabb43a7a"},"schema_version":"1.0","source":{"id":"2607.04242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04242","created_at":"2026-07-07T02:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04242v1","created_at":"2026-07-07T02:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04242","created_at":"2026-07-07T02:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"NHEN6SE7X65A","created_at":"2026-07-07T02:19:05Z"},{"alias_kind":"pith_short_16","alias_value":"NHEN6SE7X65ANL2G","created_at":"2026-07-07T02:19:05Z"},{"alias_kind":"pith_short_8","alias_value":"NHEN6SE7","created_at":"2026-07-07T02:19:05Z"}],"graph_snapshots":[{"event_id":"sha256:a136dbdef3d68ed86b9d70cdb12830f01e5c89f8747c8dafed1e0e4db7cc10b5","target":"graph","created_at":"2026-07-07T02:19:05Z","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/2607.04242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks. To obtain finer-grained policy updates than trajectory-level optimization, recent work has moved toward step-level group-based RL, where intermediate steps are grouped and compared within a rollout batch. However, step-level advantage estimation is sensitive to how groups are formed: grouping by broad state keys improves coverage but may compare actions taken under different histories, while enforcing historical consistency yields fairer comparis","authors_text":"Mingxuan Fan, Peiyang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T11:41:46Z","title":"Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04242","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":"sha256:913c0de1c96057acffe28fa4cb2ab94ecf842172e27cd6f0d289fa8a535fad59","target":"record","created_at":"2026-07-07T02:19:05Z","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":"a6cf1391a1b317dcf4f8615fa7e21ee92ac4b063e1d31f89f2d9ff0079a5e9b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T11:41:46Z","title_canon_sha256":"7d53321fafee852abfe8802b30ac2e777719168c068f2c6918b7090cabb43a7a"},"schema_version":"1.0","source":{"id":"2607.04242","kind":"arxiv","version":1}},"canonical_sha256":"69c8df489fbfba06af462c2e53b2ef929c3ee274ccf01c39d79aad106757db35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69c8df489fbfba06af462c2e53b2ef929c3ee274ccf01c39d79aad106757db35","first_computed_at":"2026-07-07T02:19:05.045313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:05.045313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ysg+WJKctXLmX9766xn5omOa+gHaxD1EsSxtzswO+kSmGdtmFg03HyGWrlBn9bTevG7zDNgbP3NAmXrVvWOXCQ==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:05.046178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:913c0de1c96057acffe28fa4cb2ab94ecf842172e27cd6f0d289fa8a535fad59","sha256:a136dbdef3d68ed86b9d70cdb12830f01e5c89f8747c8dafed1e0e4db7cc10b5"],"state_sha256":"db685527b4c35e8bd4b64b214b1ee61223c84ef6fa5727f16f078c932934ca6b"}