{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NHEN6SE7X65ANL2GFQXFHMXPSK","short_pith_number":"pith:NHEN6SE7","schema_version":"1.0","canonical_sha256":"69c8df489fbfba06af462c2e53b2ef929c3ee274ccf01c39d79aad106757db35","source":{"kind":"arxiv","id":"2607.04242","version":1},"attestation_state":"computed","paper":{"title":"Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mingxuan Fan, Peiyang Liu","submitted_at":"2026-07-05T11:41:46Z","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"},"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":"2607.04242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T11:41:46Z","cross_cats_sorted":[],"title_canon_sha256":"7d53321fafee852abfe8802b30ac2e777719168c068f2c6918b7090cabb43a7a","abstract_canon_sha256":"a6cf1391a1b317dcf4f8615fa7e21ee92ac4b063e1d31f89f2d9ff0079a5e9b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:05.046178Z","signature_b64":"Ysg+WJKctXLmX9766xn5omOa+gHaxD1EsSxtzswO+kSmGdtmFg03HyGWrlBn9bTevG7zDNgbP3NAmXrVvWOXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c8df489fbfba06af462c2e53b2ef929c3ee274ccf01c39d79aad106757db35","last_reissued_at":"2026-07-07T02:19:05.045313Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:05.045313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mingxuan Fan, Peiyang Liu","submitted_at":"2026-07-05T11:41:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04242","kind":"arxiv","version":1},"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/2607.04242/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":"2607.04242","created_at":"2026-07-07T02:19:05.045500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04242v1","created_at":"2026-07-07T02:19:05.045500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04242","created_at":"2026-07-07T02:19:05.045500+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHEN6SE7X65A","created_at":"2026-07-07T02:19:05.045500+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHEN6SE7X65ANL2G","created_at":"2026-07-07T02:19:05.045500+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHEN6SE7","created_at":"2026-07-07T02:19:05.045500+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/NHEN6SE7X65ANL2GFQXFHMXPSK","json":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK.json","graph_json":"https://pith.science/api/pith-number/NHEN6SE7X65ANL2GFQXFHMXPSK/graph.json","events_json":"https://pith.science/api/pith-number/NHEN6SE7X65ANL2GFQXFHMXPSK/events.json","paper":"https://pith.science/paper/NHEN6SE7"},"agent_actions":{"view_html":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK","download_json":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK.json","view_paper":"https://pith.science/paper/NHEN6SE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04242&json=true","fetch_graph":"https://pith.science/api/pith-number/NHEN6SE7X65ANL2GFQXFHMXPSK/graph.json","fetch_events":"https://pith.science/api/pith-number/NHEN6SE7X65ANL2GFQXFHMXPSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK/action/storage_attestation","attest_author":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK/action/author_attestation","sign_citation":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK/action/citation_signature","submit_replication":"https://pith.science/pith/NHEN6SE7X65ANL2GFQXFHMXPSK/action/replication_record"}},"created_at":"2026-07-07T02:19:05.045500+00:00","updated_at":"2026-07-07T02:19:05.045500+00:00"}