{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:G4M2M5LTJXZBDEDFZXB7JHOBC3","short_pith_number":"pith:G4M2M5LT","canonical_record":{"source":{"id":"1908.04573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T10:55:24Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"f0396e5df56ea158bebab5451d472c1abbed6ebad378732c2443b30bcb909b42","abstract_canon_sha256":"e4d01465ce8c541c2c89c265fbe93e7e014d728a04216e9c8b34c61cb22ab16c"},"schema_version":"1.0"},"canonical_sha256":"3719a675734df2119065cdc3f49dc116e6a724d52903bb39b5a9816401887fed","source":{"kind":"arxiv","id":"1908.04573","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04573","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04573v2","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04573","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"pith_short_12","alias_value":"G4M2M5LTJXZB","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"pith_short_16","alias_value":"G4M2M5LTJXZBDEDF","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"pith_short_8","alias_value":"G4M2M5LT","created_at":"2026-07-04T23:57:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:G4M2M5LTJXZBDEDFZXB7JHOBC3","target":"record","payload":{"canonical_record":{"source":{"id":"1908.04573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T10:55:24Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"f0396e5df56ea158bebab5451d472c1abbed6ebad378732c2443b30bcb909b42","abstract_canon_sha256":"e4d01465ce8c541c2c89c265fbe93e7e014d728a04216e9c8b34c61cb22ab16c"},"schema_version":"1.0"},"canonical_sha256":"3719a675734df2119065cdc3f49dc116e6a724d52903bb39b5a9816401887fed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:57:51.795549Z","signature_b64":"9ZR8jbbQycqk5/KxEgapBJ+d06LLZRbwS3o7XLEVILHkUmBCLLmFNcPHRqhXONKfAlKxlwXpq8TZRNxTtzd1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3719a675734df2119065cdc3f49dc116e6a724d52903bb39b5a9816401887fed","last_reissued_at":"2026-07-04T23:57:51.795170Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:57:51.795170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.04573","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:57:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKG/+yBe3/OKjUpeVnbjaQcrG9eCPUbI8kwTVeXDOcYprzTXsNGo1ZXmF8ZS2MzGfCzp2tIOo5Ec0ZcE6sVPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:05:54.560519Z"},"content_sha256":"0a13db3253929582416b16093d8a37b62556d4d84da57977f22672bfde0ea2d8","schema_version":"1.0","event_id":"sha256:0a13db3253929582416b16093d8a37b62556d4d84da57977f22672bfde0ea2d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:G4M2M5LTJXZBDEDFZXB7JHOBC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenwei Zhang, Lixin Cui, Lu Bai, Philip S. Yu, Yao Wan, Yue Wang","submitted_at":"2019-08-13T10:55:24Z","abstract_excerpt":"Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in similar future tasks. This paper investigates the counterfactual thinking for agents to find optimal decision-making strategies in multi-agent reinforcement learning environments. In particular, we propose a multi-agent deep reinforcement learning model with a structure which mimics the human-psychological counterfactual thinking process to impr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04573","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/1908.04573/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":"2026-07-04T23:57:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C4i7XmCiJIbkbvkBDk/WQm91pBZp1jU81sV4bBpp7umf4J1EdxiDMWa6PGRAK076rIWc48VU+1RSsRJs8sL/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:05:54.561084Z"},"content_sha256":"57500223636dd7565314873a3b800015cb5eb0a38ade5214e0ad23eadc1a05e7","schema_version":"1.0","event_id":"sha256:57500223636dd7565314873a3b800015cb5eb0a38ade5214e0ad23eadc1a05e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4M2M5LTJXZBDEDFZXB7JHOBC3/bundle.json","state_url":"https://pith.science/pith/G4M2M5LTJXZBDEDFZXB7JHOBC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4M2M5LTJXZBDEDFZXB7JHOBC3/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":"2026-08-16T09:05:54Z","links":{"resolver":"https://pith.science/pith/G4M2M5LTJXZBDEDFZXB7JHOBC3","bundle":"https://pith.science/pith/G4M2M5LTJXZBDEDFZXB7JHOBC3/bundle.json","state":"https://pith.science/pith/G4M2M5LTJXZBDEDFZXB7JHOBC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4M2M5LTJXZBDEDFZXB7JHOBC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:G4M2M5LTJXZBDEDFZXB7JHOBC3","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":"e4d01465ce8c541c2c89c265fbe93e7e014d728a04216e9c8b34c61cb22ab16c","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T10:55:24Z","title_canon_sha256":"f0396e5df56ea158bebab5451d472c1abbed6ebad378732c2443b30bcb909b42"},"schema_version":"1.0","source":{"id":"1908.04573","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04573","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04573v2","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04573","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"pith_short_12","alias_value":"G4M2M5LTJXZB","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"pith_short_16","alias_value":"G4M2M5LTJXZBDEDF","created_at":"2026-07-04T23:57:51Z"},{"alias_kind":"pith_short_8","alias_value":"G4M2M5LT","created_at":"2026-07-04T23:57:51Z"}],"graph_snapshots":[{"event_id":"sha256:57500223636dd7565314873a3b800015cb5eb0a38ade5214e0ad23eadc1a05e7","target":"graph","created_at":"2026-07-04T23:57:51Z","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/1908.04573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in similar future tasks. This paper investigates the counterfactual thinking for agents to find optimal decision-making strategies in multi-agent reinforcement learning environments. In particular, we propose a multi-agent deep reinforcement learning model with a structure which mimics the human-psychological counterfactual thinking process to impr","authors_text":"Chenwei Zhang, Lixin Cui, Lu Bai, Philip S. Yu, Yao Wan, Yue Wang","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T10:55:24Z","title":"Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04573","kind":"arxiv","version":2},"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":"sha256:0a13db3253929582416b16093d8a37b62556d4d84da57977f22672bfde0ea2d8","target":"record","created_at":"2026-07-04T23:57:51Z","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":"e4d01465ce8c541c2c89c265fbe93e7e014d728a04216e9c8b34c61cb22ab16c","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T10:55:24Z","title_canon_sha256":"f0396e5df56ea158bebab5451d472c1abbed6ebad378732c2443b30bcb909b42"},"schema_version":"1.0","source":{"id":"1908.04573","kind":"arxiv","version":2}},"canonical_sha256":"3719a675734df2119065cdc3f49dc116e6a724d52903bb39b5a9816401887fed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3719a675734df2119065cdc3f49dc116e6a724d52903bb39b5a9816401887fed","first_computed_at":"2026-07-04T23:57:51.795170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:57:51.795170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ZR8jbbQycqk5/KxEgapBJ+d06LLZRbwS3o7XLEVILHkUmBCLLmFNcPHRqhXONKfAlKxlwXpq8TZRNxTtzd1Bg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:57:51.795549Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04573","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a13db3253929582416b16093d8a37b62556d4d84da57977f22672bfde0ea2d8","sha256:57500223636dd7565314873a3b800015cb5eb0a38ade5214e0ad23eadc1a05e7"],"state_sha256":"e42a06c079c113ad2186b698c600a2fd74637c8dfccec7c584b5f70089b35b86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zh6lqcpsR43yo228XRZI+ScqMyH8M2tLyFI/Xh9Y7vV4uLZM6I1PIdW8sOyJPbffBGpZHY9K46YKAQKvWSrtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T09:05:54.564539Z","bundle_sha256":"0de1e62a4410e5e65b2902ed6350eca9b82590773ea4e507a3ebf83ae7c4f968"}}