{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NYDY6C2TKSY2RGFXZB2V3ND2UG","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":"3e09dd9e7bccdabfef9caada3e03e97b5aedcf61ed0ef7fb1830104d6afa76b1","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T21:13:43Z","title_canon_sha256":"2dcab5fcfbc5f5a10e4a90f3eba1607332a3e1ce2eee79ae53b7f1a34cdec093"},"schema_version":"1.0","source":{"id":"2606.08340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08340","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08340v1","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08340","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"NYDY6C2TKSY2","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"NYDY6C2TKSY2RGFX","created_at":"2026-06-09T01:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"NYDY6C2T","created_at":"2026-06-09T01:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:1c9629be7ad90b8a5bb5a8fff4f5cff03f8a3a166e325a3e630a0298a5d0c96f","target":"graph","created_at":"2026-06-09T01:05:34Z","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/2606.08340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks. Yet existing evaluations rarely test these demands together, instead emphasising single-agent tasks, short interactions, or highly structured multi-agent settings. We introduce $alem$, a JAX-based benchmark for open-ended multi-agent coordination built on Craftax-like dynamics. Alem embeds procedurally generated coordination tasks, soft specialisation, communication, and controllable coordination difficulty into a long-horizon survival world wi","authors_text":"Aidan Scannell, Alexander Rutherford, Amos Storkey, Andras Szecsenyi, Cameron Barker, Davide Paglieri, Elliot J. Crowley, Henry Gouk, Kale-ab Abebe Tessera, Tim Rockt\\\"aschel","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T21:13:43Z","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08340","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":"sha256:6eaf4f1cdfd6547e1eecce552e0f6e0dc97eb0846794ebc422b6060feadaaedd","target":"record","created_at":"2026-06-09T01:05:34Z","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":"3e09dd9e7bccdabfef9caada3e03e97b5aedcf61ed0ef7fb1830104d6afa76b1","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T21:13:43Z","title_canon_sha256":"2dcab5fcfbc5f5a10e4a90f3eba1607332a3e1ce2eee79ae53b7f1a34cdec093"},"schema_version":"1.0","source":{"id":"2606.08340","kind":"arxiv","version":1}},"canonical_sha256":"6e078f0b5354b1a898b7c8755db47aa1977cccdeb7db4bebcafaf3d8de639c9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e078f0b5354b1a898b7c8755db47aa1977cccdeb7db4bebcafaf3d8de639c9e","first_computed_at":"2026-06-09T01:05:34.039797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:34.039797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7CUdqfWdzw3hM028u27fpRfswgMWM+r6yk23kvzhaH2PeUpCG3BCD6ls1w4cLnrkl/OhMDdw+gInVA4afnBfDg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:34.040219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eaf4f1cdfd6547e1eecce552e0f6e0dc97eb0846794ebc422b6060feadaaedd","sha256:1c9629be7ad90b8a5bb5a8fff4f5cff03f8a3a166e325a3e630a0298a5d0c96f"],"state_sha256":"1473761f4578e9eec25f076313bf28182cf49ea3d00c64f501af98fe8570bd29"}