{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WB6D3BYFHUOLX3UJUDY4T34HOR","short_pith_number":"pith:WB6D3BYF","schema_version":"1.0","canonical_sha256":"b07c3d87053d1cbbee89a0f1c9ef87746cb348257ccef7b75fcda2c294cb0e61","source":{"kind":"arxiv","id":"2404.10740","version":3},"attestation_state":"computed","paper":{"title":"N-Agent Ad Hoc Teamwork","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Arrasy Rahman, Caroline Wang, Elad Liebman, Ishan Durugkar, Peter Stone","submitted_at":"2024-04-16T17:13:08Z","abstract_excerpt":"Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings. In standard fully cooperative multi-agent reinforcement learning, the learning algorithm controls $\\textit{all}$ agents in the scenario, while in ad hoc teamwork, the learning algorithm usually assumes control over only a $\\textit{single}$ agent in the scenario. However, many cooperative settings in the real world are much less restrictive. For example, in an autonomous driving scenario, a company might train its cars with the same learning algorithm, yet once on the road, these cars must c"},"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":"2404.10740","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-16T17:13:08Z","cross_cats_sorted":[],"title_canon_sha256":"6b4cd89ff7112f96b409d0d79c53abe98c2100358b8043fd36d4ff23b621dcb1","abstract_canon_sha256":"e052d3c589670c38227c1249fa67c2aed131404de627b6fb3782079a91cdccef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:39.491928Z","signature_b64":"WDPz8VeT0ZViaO970wAKvgoVJzUPSifBR0SW7xh0AgassKw1hUfG1hKhI+HVvd4bCauFSCYDGPr0dyhko4QmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b07c3d87053d1cbbee89a0f1c9ef87746cb348257ccef7b75fcda2c294cb0e61","last_reissued_at":"2026-07-05T11:54:39.491399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:39.491399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"N-Agent Ad Hoc Teamwork","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Arrasy Rahman, Caroline Wang, Elad Liebman, Ishan Durugkar, Peter Stone","submitted_at":"2024-04-16T17:13:08Z","abstract_excerpt":"Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings. In standard fully cooperative multi-agent reinforcement learning, the learning algorithm controls $\\textit{all}$ agents in the scenario, while in ad hoc teamwork, the learning algorithm usually assumes control over only a $\\textit{single}$ agent in the scenario. However, many cooperative settings in the real world are much less restrictive. For example, in an autonomous driving scenario, a company might train its cars with the same learning algorithm, yet once on the road, these cars must c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10740","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/2404.10740/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":"2404.10740","created_at":"2026-07-05T11:54:39.491479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10740v3","created_at":"2026-07-05T11:54:39.491479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10740","created_at":"2026-07-05T11:54:39.491479+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB6D3BYFHUOL","created_at":"2026-07-05T11:54:39.491479+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB6D3BYFHUOLX3UJ","created_at":"2026-07-05T11:54:39.491479+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB6D3BYF","created_at":"2026-07-05T11:54:39.491479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06399","citing_title":"CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments","ref_index":117,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR","json":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR.json","graph_json":"https://pith.science/api/pith-number/WB6D3BYFHUOLX3UJUDY4T34HOR/graph.json","events_json":"https://pith.science/api/pith-number/WB6D3BYFHUOLX3UJUDY4T34HOR/events.json","paper":"https://pith.science/paper/WB6D3BYF"},"agent_actions":{"view_html":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR","download_json":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR.json","view_paper":"https://pith.science/paper/WB6D3BYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10740&json=true","fetch_graph":"https://pith.science/api/pith-number/WB6D3BYFHUOLX3UJUDY4T34HOR/graph.json","fetch_events":"https://pith.science/api/pith-number/WB6D3BYFHUOLX3UJUDY4T34HOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/action/storage_attestation","attest_author":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/action/author_attestation","sign_citation":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/action/citation_signature","submit_replication":"https://pith.science/pith/WB6D3BYFHUOLX3UJUDY4T34HOR/action/replication_record"}},"created_at":"2026-07-05T11:54:39.491479+00:00","updated_at":"2026-07-05T11:54:39.491479+00:00"}