{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SR5SASPJKOVE2VFNXNJVMJSDMG","short_pith_number":"pith:SR5SASPJ","schema_version":"1.0","canonical_sha256":"947b2049e953aa4d54adbb53562643619fa163c7e8cffe39cc8d8c532ddd5c0a","source":{"kind":"arxiv","id":"2508.06336","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Partner Design Enables Robust Ad-hoc Teamwork","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Andreas Bulling, Anna Penzkofer, Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei","submitted_at":"2025-08-08T14:11:15Z","abstract_excerpt":"We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and can be extended to joint partner-environment selection when a procedural level generator is available. Across Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, UPD consi"},"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":"2508.06336","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-08T14:11:15Z","cross_cats_sorted":["cs.AI","cs.HC","cs.MA"],"title_canon_sha256":"f7ce603de1452d840b5799cb6e43a0c5ed935e60ec3ddd6e567df001a5cd93fe","abstract_canon_sha256":"a3911457bac56d4dd90a29da241f59f26d210a68e3b776e91540a7b8f6f01368"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:08.714149Z","signature_b64":"ZSzP8gOjBQES5meeA/oXjiWwBFt8odeRawPdAydVyxn2TO9C+VKgJy1J+BsE6FlbPhuhhyfn4PICK7PWCKOICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"947b2049e953aa4d54adbb53562643619fa163c7e8cffe39cc8d8c532ddd5c0a","last_reissued_at":"2026-06-09T01:05:08.713514Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:08.713514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Partner Design Enables Robust Ad-hoc Teamwork","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Andreas Bulling, Anna Penzkofer, Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei","submitted_at":"2025-08-08T14:11:15Z","abstract_excerpt":"We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and can be extended to joint partner-environment selection when a procedural level generator is available. Across Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, UPD consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06336","kind":"arxiv","version":2},"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/2508.06336/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":"2508.06336","created_at":"2026-06-09T01:05:08.713570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06336v2","created_at":"2026-06-09T01:05:08.713570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06336","created_at":"2026-06-09T01:05:08.713570+00:00"},{"alias_kind":"pith_short_12","alias_value":"SR5SASPJKOVE","created_at":"2026-06-09T01:05:08.713570+00:00"},{"alias_kind":"pith_short_16","alias_value":"SR5SASPJKOVE2VFN","created_at":"2026-06-09T01:05:08.713570+00:00"},{"alias_kind":"pith_short_8","alias_value":"SR5SASPJ","created_at":"2026-06-09T01:05:08.713570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.01358","citing_title":"PACE: Parameter Change for Unsupervised Environment Design","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG","json":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG.json","graph_json":"https://pith.science/api/pith-number/SR5SASPJKOVE2VFNXNJVMJSDMG/graph.json","events_json":"https://pith.science/api/pith-number/SR5SASPJKOVE2VFNXNJVMJSDMG/events.json","paper":"https://pith.science/paper/SR5SASPJ"},"agent_actions":{"view_html":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG","download_json":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG.json","view_paper":"https://pith.science/paper/SR5SASPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06336&json=true","fetch_graph":"https://pith.science/api/pith-number/SR5SASPJKOVE2VFNXNJVMJSDMG/graph.json","fetch_events":"https://pith.science/api/pith-number/SR5SASPJKOVE2VFNXNJVMJSDMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG/action/storage_attestation","attest_author":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG/action/author_attestation","sign_citation":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG/action/citation_signature","submit_replication":"https://pith.science/pith/SR5SASPJKOVE2VFNXNJVMJSDMG/action/replication_record"}},"created_at":"2026-06-09T01:05:08.713570+00:00","updated_at":"2026-06-09T01:05:08.713570+00:00"}