{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N4LROOLBRBTWVYML4YKFK2U2SD","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":"fa2330947244f24b7f248764ac540b2099409e0a19ef270d81d47f103a8d1808","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T06:39:21Z","title_canon_sha256":"52175301495208e940d67a1e133cf1654b907c65d00592b9f8710fa1a2e56689"},"schema_version":"1.0","source":{"id":"2605.24423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24423","created_at":"2026-05-26T01:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24423v1","created_at":"2026-05-26T01:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24423","created_at":"2026-05-26T01:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"N4LROOLBRBTW","created_at":"2026-05-26T01:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"N4LROOLBRBTWVYML","created_at":"2026-05-26T01:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"N4LROOLB","created_at":"2026-05-26T01:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:625143b1bfe420100322e2bf4dc568e25f69465ccf15c2051a23ff8e304fb6cd","target":"graph","created_at":"2026-05-26T01:03:39Z","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/2605.24423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordination with unknown partners is required-remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark ICRL4AHT, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides a reproducible end-to-end pipeline for teammate generation, learning-history collec","authors_text":"Jiajun Zhang, Jian Cheng, Jiaxi Yang, Jinmin He, Junliang Xing, Kai Li, Lei Zhang, Yuheng Jing, Zeyao Ma, Zhe Wu, Ziwen Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T06:39:21Z","title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24423","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":"sha256:3aa38385c755bbb84028c955b49a8ebe579711db9a9ee8530485a52989984a69","target":"record","created_at":"2026-05-26T01:03:39Z","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":"fa2330947244f24b7f248764ac540b2099409e0a19ef270d81d47f103a8d1808","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T06:39:21Z","title_canon_sha256":"52175301495208e940d67a1e133cf1654b907c65d00592b9f8710fa1a2e56689"},"schema_version":"1.0","source":{"id":"2605.24423","kind":"arxiv","version":1}},"canonical_sha256":"6f1717396188676ae18be614556a9a90d544a370cb191893d18f4f5cea63bb98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f1717396188676ae18be614556a9a90d544a370cb191893d18f4f5cea63bb98","first_computed_at":"2026-05-26T01:03:39.014963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:39.014963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SGQrk6/yB+SlDRPhQ+psz0xWSaC2KT4H9iZ2wiDT72P7ZjibT4e20w1f2Q/ZWrh/zj/eg6G0a++9gAAlwAD7Bw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:39.015764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aa38385c755bbb84028c955b49a8ebe579711db9a9ee8530485a52989984a69","sha256:625143b1bfe420100322e2bf4dc568e25f69465ccf15c2051a23ff8e304fb6cd"],"state_sha256":"56c5302b495bb91c9c76f353837b8f7ae3e5e420ed3acb3315ce86f53d17f3a3"}