{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SGSP55PQO3WDV65ABXYNUVDW6A","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":"4e6a8382b62da7395159cba6cb3383a7c262dc14ebeb760a37f9e19ab5d883d0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-08-02T18:14:40Z","title_canon_sha256":"b2b6a39565a29f689713302395e6dfef6d5dbdfb39745fb19ddb73fab954095f"},"schema_version":"1.0","source":{"id":"2608.01425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01425","created_at":"2026-08-04T02:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01425v1","created_at":"2026-08-04T02:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01425","created_at":"2026-08-04T02:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"SGSP55PQO3WD","created_at":"2026-08-04T02:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"SGSP55PQO3WDV65A","created_at":"2026-08-04T02:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"SGSP55PQ","created_at":"2026-08-04T02:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:a390d73b54cf2032eef69d5388b4336c11556a7a5370e7e39474db8bcbfbd6dc","target":"graph","created_at":"2026-08-04T02:05:12Z","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/2608.01425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that such systems should be judged by their behavior, not only their reward. We take up both threads in spatial cooperative games, where small frozen LLMs prompted with low-level actions fail outright, earning zero reward. Guided by the options/semi-MDP framework---and, because option execution is asynchronous across agents, its multi-agent extension in macro-action Dec-POMDPs---we equip each game with a library of symbolic \\emph{options}: typed, state-","authors_text":"Andrew Perrault, Yi Mao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-08-02T18:14:40Z","title":"Training Small LLMs as Spatial Multi-Agent Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01425","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":"sha256:7b79218544d5a191ce0928a9d41f1e6d68900ff64b2c40257e39ec5b80730454","target":"record","created_at":"2026-08-04T02:05:12Z","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":"4e6a8382b62da7395159cba6cb3383a7c262dc14ebeb760a37f9e19ab5d883d0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-08-02T18:14:40Z","title_canon_sha256":"b2b6a39565a29f689713302395e6dfef6d5dbdfb39745fb19ddb73fab954095f"},"schema_version":"1.0","source":{"id":"2608.01425","kind":"arxiv","version":1}},"canonical_sha256":"91a4fef5f076ec3afba00df0da5476f02762394211e08a1efef66a688929faec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91a4fef5f076ec3afba00df0da5476f02762394211e08a1efef66a688929faec","first_computed_at":"2026-08-04T02:05:12.122854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:05:12.122854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60qf3bwIu0Onh2GycdG8GjTkEdb9vxvvBmHH42FGyJcGL4jOUGBa/y0Oyi04hGYiO6ybS7IPOI92OrYlu3h6BQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:05:12.124443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b79218544d5a191ce0928a9d41f1e6d68900ff64b2c40257e39ec5b80730454","sha256:a390d73b54cf2032eef69d5388b4336c11556a7a5370e7e39474db8bcbfbd6dc"],"state_sha256":"a54f861fa85eefebee43a6c524b1dc6ecc32bb1a2b7b54f578cd2d7217a01fa3"}