{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AVQ6UYNYINAIXXDZAA2PZHZC4P","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":"3924ca7e473c444628e6c4d18309eea4f4488a40c06423c4b8885251a40cb83b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-17T22:55:33Z","title_canon_sha256":"d03da1d396f42bf9ecd948d64e5b037be443ca868afee9f7be75eb5ac98bbd7c"},"schema_version":"1.0","source":{"id":"2501.10593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10593","created_at":"2026-07-05T10:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10593v1","created_at":"2026-07-05T10:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10593","created_at":"2026-07-05T10:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"AVQ6UYNYINAI","created_at":"2026-07-05T10:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"AVQ6UYNYINAIXXDZ","created_at":"2026-07-05T10:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"AVQ6UYNY","created_at":"2026-07-05T10:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:e3ba47e83b4d6702c442b3391a93a26453f5216d0091734049c12cbc87b8f526","target":"graph","created_at":"2026-07-05T10:02:30Z","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/2501.10593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents' interactions with humans are increasingly focused on adapting to their changing preferences in order to improve assistance in real-world tasks. Effective agents must learn to accurately infer human goals, which are often hidden, to collaborate well. However, existing Multi-Agent Reinforcement Learning (MARL) environments lack the necessary attributes required to rigorously evaluate these agents' learning capabilities. To this end, we introduce ColorGrid, a novel MARL environment with customizable non-stationarity, asymmetry, and reward structure. We investigate the performan","authors_text":"Alan Fan, Andrey Risukhin, Ben Caffee, Kavel Rao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-17T22:55:33Z","title":"ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10593","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":"sha256:383de936e27e4b1cc648c9b9a2d07e30d9893057204e5a84d1da9b4e54ee96b3","target":"record","created_at":"2026-07-05T10:02:30Z","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":"3924ca7e473c444628e6c4d18309eea4f4488a40c06423c4b8885251a40cb83b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-17T22:55:33Z","title_canon_sha256":"d03da1d396f42bf9ecd948d64e5b037be443ca868afee9f7be75eb5ac98bbd7c"},"schema_version":"1.0","source":{"id":"2501.10593","kind":"arxiv","version":1}},"canonical_sha256":"0561ea61b843408bdc790034fc9f22e3e7c9e46188e01a1de67a2df0b5f6f749","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0561ea61b843408bdc790034fc9f22e3e7c9e46188e01a1de67a2df0b5f6f749","first_computed_at":"2026-07-05T10:02:30.449071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:30.449071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nlr5XtsoEyVafgU/lcvC2KoLPji010IalNtaraWQTkV8oiJuO1rBbBxKfOTOJDMti3FoTJB1ki41R6qI4syEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:30.449494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:383de936e27e4b1cc648c9b9a2d07e30d9893057204e5a84d1da9b4e54ee96b3","sha256:e3ba47e83b4d6702c442b3391a93a26453f5216d0091734049c12cbc87b8f526"],"state_sha256":"a82b818b4fe0b5457c1d04851f81f40119f775b8ec1169e0a9bcb72069fe40b3"}