{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AB7JQ2UVM37ISZOBWAMBXSCG32","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":"b68098f9d85154fe70720976a2d6705143b6c888c334f6726c75239dfae8d9d4","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T15:09:33Z","title_canon_sha256":"8222f60c5ff683164cf006719aace5c438427d2d8655f66f06b2e536f6a76c99"},"schema_version":"1.0","source":{"id":"2106.05802","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05802","created_at":"2026-07-05T04:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05802v2","created_at":"2026-07-05T04:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05802","created_at":"2026-07-05T04:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"AB7JQ2UVM37I","created_at":"2026-07-05T04:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"AB7JQ2UVM37ISZOB","created_at":"2026-07-05T04:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"AB7JQ2UV","created_at":"2026-07-05T04:33:19Z"}],"graph_snapshots":[{"event_id":"sha256:75cb6b741f21a454f932581c914b5d26859aefe6bf65188bd2cb44a02b4946d8","target":"graph","created_at":"2026-07-05T04:33:19Z","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/2106.05802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multi-agent reinforcement learning, the inherent non-stationarity of the environment caused by other agents' actions posed significant difficulties for an agent to learn a good policy independently. One way to deal with non-stationarity is opponent modeling, by which the agent takes into consideration the influence of other agents' policies. Most existing work relies on predicting other agents' actions or goals, or discriminating between different policies. However, such modeling fails to capture the similarities and differences between policies simultaneously and thus cannot provide enough","authors_text":"Haobin Jiang, Yifan Yu, Zongqing Lu","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T15:09:33Z","title":"Metric Policy Representations for Opponent Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05802","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:aab56abd75d47ecc1c61c4e2b74318e671fe4c2237af41924ed37b8c2c009a81","target":"record","created_at":"2026-07-05T04:33:19Z","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":"b68098f9d85154fe70720976a2d6705143b6c888c334f6726c75239dfae8d9d4","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T15:09:33Z","title_canon_sha256":"8222f60c5ff683164cf006719aace5c438427d2d8655f66f06b2e536f6a76c99"},"schema_version":"1.0","source":{"id":"2106.05802","kind":"arxiv","version":2}},"canonical_sha256":"007e986a9566fe8965c1b0181bc846de820af89f03825409d1124adebaf30525","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"007e986a9566fe8965c1b0181bc846de820af89f03825409d1124adebaf30525","first_computed_at":"2026-07-05T04:33:19.828666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:19.828666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jaTzEIWKFzCx6gHf9HaBewD12vUBul+DpGeuMQMtQv8fzXNeHQUBsvYMufw2WMPjPJvUsaU+qpaSdzn83bAWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:19.829213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05802","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aab56abd75d47ecc1c61c4e2b74318e671fe4c2237af41924ed37b8c2c009a81","sha256:75cb6b741f21a454f932581c914b5d26859aefe6bf65188bd2cb44a02b4946d8"],"state_sha256":"ef774cc3b5ac5ef1ffffc157dd457b70f5e12e49bdd5539c2113fa3dad9f3c26"}