{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XLBYOIYUUVZCULEQCKHHXETS7R","short_pith_number":"pith:XLBYOIYU","canonical_record":{"source":{"id":"2201.01448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-05T04:40:13Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"56c05adf2ddb0b38c90bc5c95a1c6e842c02f8856ce29fc7402a18e9c5900388","abstract_canon_sha256":"dde773e5295bf9a6c25df1cb20b5f27e1fa6887242c5ef150465489732482833"},"schema_version":"1.0"},"canonical_sha256":"bac3872314a5722a2c90128e7b9272fc74074ba8ca6f03d0a145106001b90f44","source":{"kind":"arxiv","id":"2201.01448","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01448","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01448v1","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01448","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"XLBYOIYUUVZC","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"XLBYOIYUUVZCULEQ","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"XLBYOIYU","created_at":"2026-07-05T03:46:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XLBYOIYUUVZCULEQCKHHXETS7R","target":"record","payload":{"canonical_record":{"source":{"id":"2201.01448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-05T04:40:13Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"56c05adf2ddb0b38c90bc5c95a1c6e842c02f8856ce29fc7402a18e9c5900388","abstract_canon_sha256":"dde773e5295bf9a6c25df1cb20b5f27e1fa6887242c5ef150465489732482833"},"schema_version":"1.0"},"canonical_sha256":"bac3872314a5722a2c90128e7b9272fc74074ba8ca6f03d0a145106001b90f44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:05.728631Z","signature_b64":"vY3P0G7gFAwIZLMagCDeYTUGJiQQ5LjZqF6WihIntsIOysPBJYAjPVVyUDw1RVUP353gJ3Vz48myjO8q/F8vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bac3872314a5722a2c90128e7b9272fc74074ba8ca6f03d0a145106001b90f44","last_reissued_at":"2026-07-05T03:46:05.728195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:05.728195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.01448","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJrG7H2/1P75ocof99egW6m7odrnAFd5tGn12YDeVlF/YT9QTyYxApCqy2Kb0NZteLX1BqcDM9Fd2l1ow7QZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:37:02.111026Z"},"content_sha256":"0181192ef48697015bab7a5b49d68128a56836e2da1310787f86d33ed0090a91","schema_version":"1.0","event_id":"sha256:0181192ef48697015bab7a5b49d68128a56836e2da1310787f86d33ed0090a91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XLBYOIYUUVZCULEQCKHHXETS7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conditional Imitation Learning for Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Andy Shih, Dorsa Sadigh, Stefano Ermon","submitted_at":"2022-01-05T04:40:13Z","abstract_excerpt":"While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents to adjust their strategy based on the strategies of those around them. In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time. This setting is challenging because we must infer a new partner's "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01448","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/2201.01448/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ro3bvwEjm+ML24CS3pr3AhzuBexeHI1tJ6TLltwbuoevgOVWXVpyX1E16J/D/Mxj1+DUA/GjWEHQMmzYwff8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:37:02.111547Z"},"content_sha256":"0add5a23fd2fb4cd4d3d3dc2aaad99be182789c79cd1d2ee4655b81a0c60b96c","schema_version":"1.0","event_id":"sha256:0add5a23fd2fb4cd4d3d3dc2aaad99be182789c79cd1d2ee4655b81a0c60b96c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/bundle.json","state_url":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLBYOIYUUVZCULEQCKHHXETS7R/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T09:37:02Z","links":{"resolver":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R","bundle":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/bundle.json","state":"https://pith.science/pith/XLBYOIYUUVZCULEQCKHHXETS7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLBYOIYUUVZCULEQCKHHXETS7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XLBYOIYUUVZCULEQCKHHXETS7R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dde773e5295bf9a6c25df1cb20b5f27e1fa6887242c5ef150465489732482833","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-05T04:40:13Z","title_canon_sha256":"56c05adf2ddb0b38c90bc5c95a1c6e842c02f8856ce29fc7402a18e9c5900388"},"schema_version":"1.0","source":{"id":"2201.01448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01448","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01448v1","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01448","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"XLBYOIYUUVZC","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"XLBYOIYUUVZCULEQ","created_at":"2026-07-05T03:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"XLBYOIYU","created_at":"2026-07-05T03:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:0add5a23fd2fb4cd4d3d3dc2aaad99be182789c79cd1d2ee4655b81a0c60b96c","target":"graph","created_at":"2026-07-05T03:46:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.01448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents to adjust their strategy based on the strategies of those around them. In this work, we study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time, and we must interact with and adapt to new partners at test time. This setting is challenging because we must infer a new partner's ","authors_text":"Andy Shih, Dorsa Sadigh, Stefano Ermon","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-05T04:40:13Z","title":"Conditional Imitation Learning for Multi-Agent Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01448","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0181192ef48697015bab7a5b49d68128a56836e2da1310787f86d33ed0090a91","target":"record","created_at":"2026-07-05T03:46:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dde773e5295bf9a6c25df1cb20b5f27e1fa6887242c5ef150465489732482833","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-05T04:40:13Z","title_canon_sha256":"56c05adf2ddb0b38c90bc5c95a1c6e842c02f8856ce29fc7402a18e9c5900388"},"schema_version":"1.0","source":{"id":"2201.01448","kind":"arxiv","version":1}},"canonical_sha256":"bac3872314a5722a2c90128e7b9272fc74074ba8ca6f03d0a145106001b90f44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bac3872314a5722a2c90128e7b9272fc74074ba8ca6f03d0a145106001b90f44","first_computed_at":"2026-07-05T03:46:05.728195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:05.728195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vY3P0G7gFAwIZLMagCDeYTUGJiQQ5LjZqF6WihIntsIOysPBJYAjPVVyUDw1RVUP353gJ3Vz48myjO8q/F8vBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:05.728631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.01448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0181192ef48697015bab7a5b49d68128a56836e2da1310787f86d33ed0090a91","sha256:0add5a23fd2fb4cd4d3d3dc2aaad99be182789c79cd1d2ee4655b81a0c60b96c"],"state_sha256":"191cd3d8a1d5e22069d50bbf915f55ad74f5be54a4e0ca503de7d917160bf6c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vuxVhFa5zv53MUgU2PFA5vwMoZn+2ie+MgxaCUDOTMqgeSYweL8XWTXkeGYzMBZ7cU0nSJqYWj+sCruZyd1UCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T09:37:02.116684Z","bundle_sha256":"8f0ae789807a913ea7043ea21af16c6ed049bda3dc1efe046997940b4e8fda0d"}}