{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MJAC5SGJOL6FVX5X7LJXN5ZKPA","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":"e2a7e5beab2831864ad097fe42b1acb7f3b6ab337f82c53ffd4c2383795ed6c6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:31:10Z","title_canon_sha256":"5925b5c33f8483d507f4b5d1670f9ad78f976d577ec9dd21a67489a39a0cf037"},"schema_version":"1.0","source":{"id":"2505.11100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11100","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11100v1","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11100","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"MJAC5SGJOL6F","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"MJAC5SGJOL6FVX5X","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"MJAC5SGJ","created_at":"2026-07-05T11:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:c977bd4e865f870ba56bf6644f59b6c1f884eb7c0959fe2dda86aecd57ee1c53","target":"graph","created_at":"2026-07-05T11:04:10Z","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/2505.11100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing self-play-based methods are constrained by the limitation of inside-space generalization. In this study, we propose Bidirectional Distillation (BiDist), a novel mixed-play framework, to overcome this limitation in MARL. BiDist leverages knowledge distillation in two alternating directions: forward distillation, which emulates the historical policies' space and creates an implicit self-play, and reverse distillation, ","authors_text":"De Ma, Dong Xing, Gang Pan, Jiahao Lin, Lang Feng, Li Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:31:10Z","title":"Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11100","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":"sha256:84215dc7904bafaaf34c5456dc35768909ec8d70f91cf4d4dd4bea1b03a4df9f","target":"record","created_at":"2026-07-05T11:04:10Z","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":"e2a7e5beab2831864ad097fe42b1acb7f3b6ab337f82c53ffd4c2383795ed6c6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:31:10Z","title_canon_sha256":"5925b5c33f8483d507f4b5d1670f9ad78f976d577ec9dd21a67489a39a0cf037"},"schema_version":"1.0","source":{"id":"2505.11100","kind":"arxiv","version":1}},"canonical_sha256":"62402ec8c972fc5adfb7fad376f72a783bf6a308a7afff32d43cfdd1067c44b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62402ec8c972fc5adfb7fad376f72a783bf6a308a7afff32d43cfdd1067c44b4","first_computed_at":"2026-07-05T11:04:10.784196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:10.784196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mm+wGM5zlD6fsblllEwHHxcVv/xU0qanvrJ7IFCPnBJN2IZKG3MvJA9ATdCv2pfvgnVbh/f2Lyvg+TOPi14HCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:10.784671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84215dc7904bafaaf34c5456dc35768909ec8d70f91cf4d4dd4bea1b03a4df9f","sha256:c977bd4e865f870ba56bf6644f59b6c1f884eb7c0959fe2dda86aecd57ee1c53"],"state_sha256":"bcf336c91526d9f8d700a3c0b51e29e3b6444932380e989aa9f3eb8a48e9ba40"}