{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M3EIB7SRFNDVIXSK3ZW4WMAXFU","short_pith_number":"pith:M3EIB7SR","schema_version":"1.0","canonical_sha256":"66c880fe512b47545e4ade6dcb30172d006eef7e62cd4fdd84b7a6fb4900e103","source":{"kind":"arxiv","id":"2508.12480","version":3},"attestation_state":"computed","paper":{"title":"The Yokai Learning Environment: Tracking Beliefs Over Space and Time","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Andreas Bulling, Constantin Ruhdorfer, Jakob Foerster, Johannes Forkel, Matteo Bortoletto","submitted_at":"2025-08-17T19:42:17Z","abstract_excerpt":"The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm by measuring the performance of independently trained agents when paired. The Hanabi Learning Environment (HLE) has become the dominant benchmark for ZSC, but recent work has achieved near-perfect inter-seed cross-play performance, limiting its ability to track algorithmic progress. We introduce the Yokai Learning Environment (YLE) - an open-source multi-agent RL benchmark in which effective collaboration requires b"},"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":"2508.12480","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-17T19:42:17Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"5c51a0b38ab33e2c9070d52ba87754d3314f7860ca52173ae5b4035d6cea33f9","abstract_canon_sha256":"4ee5e38ff6c2df2bf14d5803e399d31b15191bd97169752e3066e4d07494c155"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:37:08.313418Z","signature_b64":"m1+k1dKbhhcQNlDgPwPKQR6yBfD64rua7zLVbHI9Q6JIwk8r88xZbjgmC4tPFP8f53rXkg3H12SLJZacQU8rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66c880fe512b47545e4ade6dcb30172d006eef7e62cd4fdd84b7a6fb4900e103","last_reissued_at":"2026-08-06T01:37:08.311550Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:37:08.311550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Yokai Learning Environment: Tracking Beliefs Over Space and Time","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Andreas Bulling, Constantin Ruhdorfer, Jakob Foerster, Johannes Forkel, Matteo Bortoletto","submitted_at":"2025-08-17T19:42:17Z","abstract_excerpt":"The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm by measuring the performance of independently trained agents when paired. The Hanabi Learning Environment (HLE) has become the dominant benchmark for ZSC, but recent work has achieved near-perfect inter-seed cross-play performance, limiting its ability to track algorithmic progress. We introduce the Yokai Learning Environment (YLE) - an open-source multi-agent RL benchmark in which effective collaboration requires b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12480","kind":"arxiv","version":3},"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/2508.12480/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":"2508.12480","created_at":"2026-08-06T01:37:08.313619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12480v3","created_at":"2026-08-06T01:37:08.313619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12480","created_at":"2026-08-06T01:37:08.313619+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3EIB7SRFNDV","created_at":"2026-08-06T01:37:08.313619+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3EIB7SRFNDVIXSK","created_at":"2026-08-06T01:37:08.313619+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3EIB7SR","created_at":"2026-08-06T01:37:08.313619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05091","citing_title":"ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU","json":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU.json","graph_json":"https://pith.science/api/pith-number/M3EIB7SRFNDVIXSK3ZW4WMAXFU/graph.json","events_json":"https://pith.science/api/pith-number/M3EIB7SRFNDVIXSK3ZW4WMAXFU/events.json","paper":"https://pith.science/paper/M3EIB7SR"},"agent_actions":{"view_html":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU","download_json":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU.json","view_paper":"https://pith.science/paper/M3EIB7SR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12480&json=true","fetch_graph":"https://pith.science/api/pith-number/M3EIB7SRFNDVIXSK3ZW4WMAXFU/graph.json","fetch_events":"https://pith.science/api/pith-number/M3EIB7SRFNDVIXSK3ZW4WMAXFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU/action/storage_attestation","attest_author":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU/action/author_attestation","sign_citation":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU/action/citation_signature","submit_replication":"https://pith.science/pith/M3EIB7SRFNDVIXSK3ZW4WMAXFU/action/replication_record"}},"created_at":"2026-08-06T01:37:08.313619+00:00","updated_at":"2026-08-06T01:37:08.313619+00:00"}