{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T5C6SRQJCJKRJO47XQA74FMRS5","short_pith_number":"pith:T5C6SRQJ","canonical_record":{"source":{"id":"2606.07845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-05T21:13:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9778157bb29ebff89a4fe47ffb6e11b23b19866d09d27ea43c15d69cda8c9e36","abstract_canon_sha256":"084fc308c029851a025d294b23ef9cb639e5858ac9158285bcc209d98ea04257"},"schema_version":"1.0"},"canonical_sha256":"9f45e94609125514bb9fbc01fe1591975b0f66e388b712ba4f207a4fd0e96233","source":{"kind":"arxiv","id":"2606.07845","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07845","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07845v1","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07845","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"T5C6SRQJCJKR","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"T5C6SRQJCJKRJO47","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"T5C6SRQJ","created_at":"2026-06-09T01:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T5C6SRQJCJKRJO47XQA74FMRS5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-05T21:13:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9778157bb29ebff89a4fe47ffb6e11b23b19866d09d27ea43c15d69cda8c9e36","abstract_canon_sha256":"084fc308c029851a025d294b23ef9cb639e5858ac9158285bcc209d98ea04257"},"schema_version":"1.0"},"canonical_sha256":"9f45e94609125514bb9fbc01fe1591975b0f66e388b712ba4f207a4fd0e96233","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:53.613155Z","signature_b64":"/JfXZ3aUDihj5BsPcFsRF27wts8MNcagJMLa4Hh2LGHDDdu5+So6RM+UCo9cb8sMaNGIKAoszjtBhZMGu7KCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f45e94609125514bb9fbc01fe1591975b0f66e388b712ba4f207a4fd0e96233","last_reissued_at":"2026-06-09T01:04:53.612753Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:53.612753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07845","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":"2026-06-09T01:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcWpoFU7tGr7uRoEvhFPli9f445o6G64Zb6NRbhPQBy/t2Bn1cptbzy8MPb5B9EKsUXv4IdL711oQrdqxZbJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:22:33.064655Z"},"content_sha256":"a1b7f71a74f6edc2727a200382ca3347b034ff676dd17b69c27859628f800a74","schema_version":"1.0","event_id":"sha256:a1b7f71a74f6edc2727a200382ca3347b034ff676dd17b69c27859628f800a74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T5C6SRQJCJKRJO47XQA74FMRS5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRPO Does Not Close the Multi-Agent Coordination Gap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Najmul Hasan, Prashanth Busireddygari","submitted_at":"2026-06-05T21:13:14Z","abstract_excerpt":"We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a clean test bed. Across 630 episodes spanning seven models and three philosopher counts, four frontier closed-source systems reach mean reward 0.45 to 0.87 and Mistral-Small 24B reaches 0.83 to 0.99, while Qwen3-14B reaches 0.13 to 0.35. We then ask whether group relative policy optimization (GRPO) on rollouts from the task itself can close the gap and find that it cannot: a Welch's t-test on per-episode reward at five philosophers gives p = 0.66 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07845","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/2606.07845/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":"2026-06-09T01:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEX/6+5hocnn1TafgITSr587PLuGsn6H6i0mTuJhm2qnH0JejeGuJaoYI8HuNu+0B7cMzCnzgh4MMWdc+khhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:22:33.065131Z"},"content_sha256":"81b033f939368e39dcadea2e4331588bd02414e47dfa0502d92fceaaf387ffa9","schema_version":"1.0","event_id":"sha256:81b033f939368e39dcadea2e4331588bd02414e47dfa0502d92fceaaf387ffa9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T5C6SRQJCJKRJO47XQA74FMRS5/bundle.json","state_url":"https://pith.science/pith/T5C6SRQJCJKRJO47XQA74FMRS5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T5C6SRQJCJKRJO47XQA74FMRS5/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":"2026-08-21T08:22:33Z","links":{"resolver":"https://pith.science/pith/T5C6SRQJCJKRJO47XQA74FMRS5","bundle":"https://pith.science/pith/T5C6SRQJCJKRJO47XQA74FMRS5/bundle.json","state":"https://pith.science/pith/T5C6SRQJCJKRJO47XQA74FMRS5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T5C6SRQJCJKRJO47XQA74FMRS5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T5C6SRQJCJKRJO47XQA74FMRS5","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":"084fc308c029851a025d294b23ef9cb639e5858ac9158285bcc209d98ea04257","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-05T21:13:14Z","title_canon_sha256":"9778157bb29ebff89a4fe47ffb6e11b23b19866d09d27ea43c15d69cda8c9e36"},"schema_version":"1.0","source":{"id":"2606.07845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07845","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07845v1","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07845","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"T5C6SRQJCJKR","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"T5C6SRQJCJKRJO47","created_at":"2026-06-09T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"T5C6SRQJ","created_at":"2026-06-09T01:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:81b033f939368e39dcadea2e4331588bd02414e47dfa0502d92fceaaf387ffa9","target":"graph","created_at":"2026-06-09T01:04:53Z","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/2606.07845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a clean test bed. Across 630 episodes spanning seven models and three philosopher counts, four frontier closed-source systems reach mean reward 0.45 to 0.87 and Mistral-Small 24B reaches 0.83 to 0.99, while Qwen3-14B reaches 0.13 to 0.35. We then ask whether group relative policy optimization (GRPO) on rollouts from the task itself can close the gap and find that it cannot: a Welch's t-test on per-episode reward at five philosophers gives p = 0.66 ","authors_text":"Najmul Hasan, Prashanth Busireddygari","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-05T21:13:14Z","title":"GRPO Does Not Close the Multi-Agent Coordination Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07845","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:a1b7f71a74f6edc2727a200382ca3347b034ff676dd17b69c27859628f800a74","target":"record","created_at":"2026-06-09T01:04:53Z","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":"084fc308c029851a025d294b23ef9cb639e5858ac9158285bcc209d98ea04257","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-05T21:13:14Z","title_canon_sha256":"9778157bb29ebff89a4fe47ffb6e11b23b19866d09d27ea43c15d69cda8c9e36"},"schema_version":"1.0","source":{"id":"2606.07845","kind":"arxiv","version":1}},"canonical_sha256":"9f45e94609125514bb9fbc01fe1591975b0f66e388b712ba4f207a4fd0e96233","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f45e94609125514bb9fbc01fe1591975b0f66e388b712ba4f207a4fd0e96233","first_computed_at":"2026-06-09T01:04:53.612753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:53.612753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/JfXZ3aUDihj5BsPcFsRF27wts8MNcagJMLa4Hh2LGHDDdu5+So6RM+UCo9cb8sMaNGIKAoszjtBhZMGu7KCCw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:53.613155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1b7f71a74f6edc2727a200382ca3347b034ff676dd17b69c27859628f800a74","sha256:81b033f939368e39dcadea2e4331588bd02414e47dfa0502d92fceaaf387ffa9"],"state_sha256":"18dc674f87784ffb9c52e6f7f960b5964a1c228b2910e56961e1115ff41fb263"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3067+/PWzEw+VG3LiqQ+zkuJnYL2ldwVr1Ch3H1KteVCb+xNpCct3xhaf8tw9sa9V7FK7PXvua7TKwu9uHdTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T08:22:33.067657Z","bundle_sha256":"3db93bf57bbe601289d06e8ae0287fcd78a7a8fd034f2d944b22480224180e8c"}}