{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QI5UBBB7K4E67HQ5W7D25HKDJT","short_pith_number":"pith:QI5UBBB7","canonical_record":{"source":{"id":"2508.10839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T17:05:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3101842015c8d5eeb5e3aae060dc1ccde008f17a546f81c83a0dc4eec2b094b4","abstract_canon_sha256":"5485631b0f72ad2207d7151749bda380ca3ce23adb994e04c85c88a2f9b846d4"},"schema_version":"1.0"},"canonical_sha256":"823b40843f5709ef9e1db7c7ae9d434cea5ca563f92c37e4ca79f6859874ff59","source":{"kind":"arxiv","id":"2508.10839","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10839","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10839v1","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10839","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"QI5UBBB7K4E6","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"QI5UBBB7K4E67HQ5","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"QI5UBBB7","created_at":"2026-07-05T11:54:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QI5UBBB7K4E67HQ5W7D25HKDJT","target":"record","payload":{"canonical_record":{"source":{"id":"2508.10839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T17:05:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3101842015c8d5eeb5e3aae060dc1ccde008f17a546f81c83a0dc4eec2b094b4","abstract_canon_sha256":"5485631b0f72ad2207d7151749bda380ca3ce23adb994e04c85c88a2f9b846d4"},"schema_version":"1.0"},"canonical_sha256":"823b40843f5709ef9e1db7c7ae9d434cea5ca563f92c37e4ca79f6859874ff59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:03.497267Z","signature_b64":"nuudybnqDTnJFNS4hQjdfXshRn9jfn5UzwKvAlBXNDdUFaurv7pTI3Ivr74TIOb3NF2acpIQui20wTS9Gy/TCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"823b40843f5709ef9e1db7c7ae9d434cea5ca563f92c37e4ca79f6859874ff59","last_reissued_at":"2026-07-05T11:54:03.496822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:03.496822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.10839","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vij2GgWpt59mo8pVK6mSKQPniHEvFgVgI7DA3rqfkwxYCj10tCrlJGFL9/db+DgI7ed0n0UL2z0m5QemV2kZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:02:27.451915Z"},"content_sha256":"ac503530430bb4ba9f0d817415ffcdd0e4df86bc49afaf7f4ac66731a6a01c7d","schema_version":"1.0","event_id":"sha256:ac503530430bb4ba9f0d817415ffcdd0e4df86bc49afaf7f4ac66731a6a01c7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QI5UBBB7K4E67HQ5W7D25HKDJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforced Language Models for Sequential Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jim Dilkes, Sebastian Stein, Vahid Yazdanpanah","submitted_at":"2025-08-14T17:05:44Z","abstract_excerpt":"Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive models. This creates a need to improve smaller models, yet existing post-training methods are designed for single-turn interactions and cannot handle credit assignment in multi-step agentic tasks. To address this, we introduce Multi-Step Group-Relative Policy Optimization (MS-GRPO), a new algorithm for post-training LLM agents, grounded in formal Text-Mediated Stochastic Game (TSMG) and Language-Agent Policy (LAP) framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10839","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/2508.10839/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dG9r63/8BeWySBe3fc4PxNz/MRbgPmYTtcwJoMl1ocyQVsLM1oCr6zFsobKPC1G4fYc+USj5aUN+WpywlyvMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T16:02:27.452417Z"},"content_sha256":"30ae51efcc76f6e2b0cd7a3c33b935492d1566283cb9cff150af7b977a81cf3f","schema_version":"1.0","event_id":"sha256:30ae51efcc76f6e2b0cd7a3c33b935492d1566283cb9cff150af7b977a81cf3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QI5UBBB7K4E67HQ5W7D25HKDJT/bundle.json","state_url":"https://pith.science/pith/QI5UBBB7K4E67HQ5W7D25HKDJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QI5UBBB7K4E67HQ5W7D25HKDJT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T16:02:27Z","links":{"resolver":"https://pith.science/pith/QI5UBBB7K4E67HQ5W7D25HKDJT","bundle":"https://pith.science/pith/QI5UBBB7K4E67HQ5W7D25HKDJT/bundle.json","state":"https://pith.science/pith/QI5UBBB7K4E67HQ5W7D25HKDJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QI5UBBB7K4E67HQ5W7D25HKDJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QI5UBBB7K4E67HQ5W7D25HKDJT","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":"5485631b0f72ad2207d7151749bda380ca3ce23adb994e04c85c88a2f9b846d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T17:05:44Z","title_canon_sha256":"3101842015c8d5eeb5e3aae060dc1ccde008f17a546f81c83a0dc4eec2b094b4"},"schema_version":"1.0","source":{"id":"2508.10839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10839","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10839v1","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10839","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"QI5UBBB7K4E6","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"QI5UBBB7K4E67HQ5","created_at":"2026-07-05T11:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"QI5UBBB7","created_at":"2026-07-05T11:54:03Z"}],"graph_snapshots":[{"event_id":"sha256:30ae51efcc76f6e2b0cd7a3c33b935492d1566283cb9cff150af7b977a81cf3f","target":"graph","created_at":"2026-07-05T11:54:03Z","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/2508.10839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive models. This creates a need to improve smaller models, yet existing post-training methods are designed for single-turn interactions and cannot handle credit assignment in multi-step agentic tasks. To address this, we introduce Multi-Step Group-Relative Policy Optimization (MS-GRPO), a new algorithm for post-training LLM agents, grounded in formal Text-Mediated Stochastic Game (TSMG) and Language-Agent Policy (LAP) framewo","authors_text":"Jim Dilkes, Sebastian Stein, Vahid Yazdanpanah","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T17:05:44Z","title":"Reinforced Language Models for Sequential Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10839","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:ac503530430bb4ba9f0d817415ffcdd0e4df86bc49afaf7f4ac66731a6a01c7d","target":"record","created_at":"2026-07-05T11:54:03Z","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":"5485631b0f72ad2207d7151749bda380ca3ce23adb994e04c85c88a2f9b846d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T17:05:44Z","title_canon_sha256":"3101842015c8d5eeb5e3aae060dc1ccde008f17a546f81c83a0dc4eec2b094b4"},"schema_version":"1.0","source":{"id":"2508.10839","kind":"arxiv","version":1}},"canonical_sha256":"823b40843f5709ef9e1db7c7ae9d434cea5ca563f92c37e4ca79f6859874ff59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"823b40843f5709ef9e1db7c7ae9d434cea5ca563f92c37e4ca79f6859874ff59","first_computed_at":"2026-07-05T11:54:03.496822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:03.496822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nuudybnqDTnJFNS4hQjdfXshRn9jfn5UzwKvAlBXNDdUFaurv7pTI3Ivr74TIOb3NF2acpIQui20wTS9Gy/TCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:03.497267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac503530430bb4ba9f0d817415ffcdd0e4df86bc49afaf7f4ac66731a6a01c7d","sha256:30ae51efcc76f6e2b0cd7a3c33b935492d1566283cb9cff150af7b977a81cf3f"],"state_sha256":"9dcee9e8096e06708ce7c5667a9f89ed3a0c4430c0e0c7fc2d5a0f280e67de44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0FvJE0tfdWSkJgkLWjAM2IzHO4XyPeVELZHTmH1OnnP7EbajuyFs1XvjbE+FT5hEticvc4NScRacSX8mxJKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T16:02:27.457114Z","bundle_sha256":"615df1855e310de4f7459d8f8a19919b10b42c9a97f1fd5d2ca880f53779a837"}}