{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SGSP55PQO3WDV65ABXYNUVDW6A","short_pith_number":"pith:SGSP55PQ","canonical_record":{"source":{"id":"2608.01425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-08-02T18:14:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b2b6a39565a29f689713302395e6dfef6d5dbdfb39745fb19ddb73fab954095f","abstract_canon_sha256":"4e6a8382b62da7395159cba6cb3383a7c262dc14ebeb760a37f9e19ab5d883d0"},"schema_version":"1.0"},"canonical_sha256":"91a4fef5f076ec3afba00df0da5476f02762394211e08a1efef66a688929faec","source":{"kind":"arxiv","id":"2608.01425","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SGSP55PQO3WDV65ABXYNUVDW6A","target":"record","payload":{"canonical_record":{"source":{"id":"2608.01425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-08-02T18:14:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b2b6a39565a29f689713302395e6dfef6d5dbdfb39745fb19ddb73fab954095f","abstract_canon_sha256":"4e6a8382b62da7395159cba6cb3383a7c262dc14ebeb760a37f9e19ab5d883d0"},"schema_version":"1.0"},"canonical_sha256":"91a4fef5f076ec3afba00df0da5476f02762394211e08a1efef66a688929faec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:05:12.124443Z","signature_b64":"60qf3bwIu0Onh2GycdG8GjTkEdb9vxvvBmHH42FGyJcGL4jOUGBa/y0Oyi04hGYiO6ybS7IPOI92OrYlu3h6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a4fef5f076ec3afba00df0da5476f02762394211e08a1efef66a688929faec","last_reissued_at":"2026-08-04T02:05:12.122854Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:05:12.122854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.01425","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":"2026-08-04T02:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPvEu5Cd+YbAYX3L4/qhLIfAeYixO1leZHTUpEedK5wU9VLPwTCh9VacVMthd4S+MuE8G3GTCw3A1jLWP+lQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:02:58.596339Z"},"content_sha256":"7b79218544d5a191ce0928a9d41f1e6d68900ff64b2c40257e39ec5b80730454","schema_version":"1.0","event_id":"sha256:7b79218544d5a191ce0928a9d41f1e6d68900ff64b2c40257e39ec5b80730454"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SGSP55PQO3WDV65ABXYNUVDW6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Small LLMs as Spatial Multi-Agent Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Andrew Perrault, Yi Mao","submitted_at":"2026-08-02T18:14:40Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01425","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/2608.01425/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":"2026-08-04T02:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjoNVSa7XhsOvvegrsNPs5MtXFUzapKgjk8Dq7Tq0pdf18AbEDr+Y9BWp5bGAfp8/4JSfuVlsSmH2Szf65vfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:02:58.596975Z"},"content_sha256":"a390d73b54cf2032eef69d5388b4336c11556a7a5370e7e39474db8bcbfbd6dc","schema_version":"1.0","event_id":"sha256:a390d73b54cf2032eef69d5388b4336c11556a7a5370e7e39474db8bcbfbd6dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGSP55PQO3WDV65ABXYNUVDW6A/bundle.json","state_url":"https://pith.science/pith/SGSP55PQO3WDV65ABXYNUVDW6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGSP55PQO3WDV65ABXYNUVDW6A/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":"2026-08-06T16:02:58Z","links":{"resolver":"https://pith.science/pith/SGSP55PQO3WDV65ABXYNUVDW6A","bundle":"https://pith.science/pith/SGSP55PQO3WDV65ABXYNUVDW6A/bundle.json","state":"https://pith.science/pith/SGSP55PQO3WDV65ABXYNUVDW6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGSP55PQO3WDV65ABXYNUVDW6A/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2dkiBqbawqv3f/6xoFWUfbM/l/JjItzgULN1DCIxIxCbc75QxTlvbll0EMqiNJCO4t/jd1Eo0/BSAH+h8kUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:02:58.603785Z","bundle_sha256":"77d26f65073c5ba2ddeb05c654a456df65549adba4f27725fb6bf80e167636fe"}}