{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AVQ6UYNYINAIXXDZAA2PZHZC4P","short_pith_number":"pith:AVQ6UYNY","schema_version":"1.0","canonical_sha256":"0561ea61b843408bdc790034fc9f22e3e7c9e46188e01a1de67a2df0b5f6f749","source":{"kind":"arxiv","id":"2501.10593","version":1},"attestation_state":"computed","paper":{"title":"ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alan Fan, Andrey Risukhin, Ben Caffee, Kavel Rao","submitted_at":"2025-01-17T22:55:33Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.10593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-17T22:55:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d03da1d396f42bf9ecd948d64e5b037be443ca868afee9f7be75eb5ac98bbd7c","abstract_canon_sha256":"3924ca7e473c444628e6c4d18309eea4f4488a40c06423c4b8885251a40cb83b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:30.449494Z","signature_b64":"Nlr5XtsoEyVafgU/lcvC2KoLPji010IalNtaraWQTkV8oiJuO1rBbBxKfOTOJDMti3FoTJB1ki41R6qI4syEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0561ea61b843408bdc790034fc9f22e3e7c9e46188e01a1de67a2df0b5f6f749","last_reissued_at":"2026-07-05T10:02:30.449071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:30.449071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alan Fan, Andrey Risukhin, Ben Caffee, Kavel Rao","submitted_at":"2025-01-17T22:55:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10593","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/2501.10593/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.10593","created_at":"2026-07-05T10:02:30.449145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10593v1","created_at":"2026-07-05T10:02:30.449145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10593","created_at":"2026-07-05T10:02:30.449145+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVQ6UYNYINAI","created_at":"2026-07-05T10:02:30.449145+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVQ6UYNYINAIXXDZ","created_at":"2026-07-05T10:02:30.449145+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVQ6UYNY","created_at":"2026-07-05T10:02:30.449145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P","json":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P.json","graph_json":"https://pith.science/api/pith-number/AVQ6UYNYINAIXXDZAA2PZHZC4P/graph.json","events_json":"https://pith.science/api/pith-number/AVQ6UYNYINAIXXDZAA2PZHZC4P/events.json","paper":"https://pith.science/paper/AVQ6UYNY"},"agent_actions":{"view_html":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P","download_json":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P.json","view_paper":"https://pith.science/paper/AVQ6UYNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10593&json=true","fetch_graph":"https://pith.science/api/pith-number/AVQ6UYNYINAIXXDZAA2PZHZC4P/graph.json","fetch_events":"https://pith.science/api/pith-number/AVQ6UYNYINAIXXDZAA2PZHZC4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P/action/storage_attestation","attest_author":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P/action/author_attestation","sign_citation":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P/action/citation_signature","submit_replication":"https://pith.science/pith/AVQ6UYNYINAIXXDZAA2PZHZC4P/action/replication_record"}},"created_at":"2026-07-05T10:02:30.449145+00:00","updated_at":"2026-07-05T10:02:30.449145+00:00"}