{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HG5OPIB37D74A3JNDAG7733MTT","short_pith_number":"pith:HG5OPIB3","schema_version":"1.0","canonical_sha256":"39bae7a03bf8ffc06d2d180dffef6c9cd70b959af02f6f29b74766ea11db4242","source":{"kind":"arxiv","id":"2506.23549","version":3},"attestation_state":"computed","paper":{"title":"CooT: Learning to Coordinate In-Context with Coordination Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dai-Jie Wu, Hsiang-Chun Chuang, Hsi-Chun Cheng, Huai-Chih Wang, Shao-Hua Sun","submitted_at":"2025-06-30T06:45:39Z","abstract_excerpt":"Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as population-based methods, improve robustness through diversity but often lack mechanisms for efficient adaptation beyond training distribution. Moreover, fine-tuning is impractical in few-shot settings due to its high interaction cost. To address these limitations, we propose CooT, a framework that leverages in-context learning (ICL) for real-time partner adaptation. Unlike prior ICL approaches that focus on task generalization, CooT is designed to generalize across d"},"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":"2506.23549","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-30T06:45:39Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"053f0fe6f5d5dbcb97f080da71974bee22f130f8c87cc005249e292cd4b8b0d5","abstract_canon_sha256":"69d46425e2a306ef59c276daf45606e8e30a65c2fc2684bcf184c5c4e3b114a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:11.483162Z","signature_b64":"ikzOJnBqMCMrKXakRfUFrdzThubdsOZGkthDDC5QOE//nVxF44UFs+yqDQPFCjcaGePSNbFyumUWThZU+aCNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39bae7a03bf8ffc06d2d180dffef6c9cd70b959af02f6f29b74766ea11db4242","last_reissued_at":"2026-05-20T00:04:11.482434Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:11.482434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CooT: Learning to Coordinate In-Context with Coordination Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dai-Jie Wu, Hsiang-Chun Chuang, Hsi-Chun Cheng, Huai-Chih Wang, Shao-Hua Sun","submitted_at":"2025-06-30T06:45:39Z","abstract_excerpt":"Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as population-based methods, improve robustness through diversity but often lack mechanisms for efficient adaptation beyond training distribution. Moreover, fine-tuning is impractical in few-shot settings due to its high interaction cost. To address these limitations, we propose CooT, a framework that leverages in-context learning (ICL) for real-time partner adaptation. Unlike prior ICL approaches that focus on task generalization, CooT is designed to generalize across d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23549","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/2506.23549/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":"2506.23549","created_at":"2026-05-20T00:04:11.482564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23549v3","created_at":"2026-05-20T00:04:11.482564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23549","created_at":"2026-05-20T00:04:11.482564+00:00"},{"alias_kind":"pith_short_12","alias_value":"HG5OPIB37D74","created_at":"2026-05-20T00:04:11.482564+00:00"},{"alias_kind":"pith_short_16","alias_value":"HG5OPIB37D74A3JN","created_at":"2026-05-20T00:04:11.482564+00:00"},{"alias_kind":"pith_short_8","alias_value":"HG5OPIB3","created_at":"2026-05-20T00:04:11.482564+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/HG5OPIB37D74A3JNDAG7733MTT","json":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT.json","graph_json":"https://pith.science/api/pith-number/HG5OPIB37D74A3JNDAG7733MTT/graph.json","events_json":"https://pith.science/api/pith-number/HG5OPIB37D74A3JNDAG7733MTT/events.json","paper":"https://pith.science/paper/HG5OPIB3"},"agent_actions":{"view_html":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT","download_json":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT.json","view_paper":"https://pith.science/paper/HG5OPIB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23549&json=true","fetch_graph":"https://pith.science/api/pith-number/HG5OPIB37D74A3JNDAG7733MTT/graph.json","fetch_events":"https://pith.science/api/pith-number/HG5OPIB37D74A3JNDAG7733MTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT/action/storage_attestation","attest_author":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT/action/author_attestation","sign_citation":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT/action/citation_signature","submit_replication":"https://pith.science/pith/HG5OPIB37D74A3JNDAG7733MTT/action/replication_record"}},"created_at":"2026-05-20T00:04:11.482564+00:00","updated_at":"2026-05-20T00:04:11.482564+00:00"}