{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IICL7AUIRS2F2PDFFFXUL3KFIR","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":"65d62ffef62172e062a86cdb2720a97363da05faa9afd209561d9fb0abc05233","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T13:33:31Z","title_canon_sha256":"a713b35b1c6064338003fac3b6335d0169a36e6de997835efb32e16da467f373"},"schema_version":"1.0","source":{"id":"2509.06053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06053","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06053v1","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06053","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"IICL7AUIRS2F","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"IICL7AUIRS2F2PDF","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"IICL7AUI","created_at":"2026-07-05T12:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:1e8c96d8e1bde5895755f30d84d903078bff4edf89f341b5f321997cef89d29d","target":"graph","created_at":"2026-07-05T12:06:29Z","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/2509.06053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) has achieved significant progress in solving complex multi-player games through self-play. However, training effective adversarial policies requires millions of experience samples and substantial computational resources. Moreover, these policies lack interpretability, hindering their practical deployment. Recently, researchers have successfully leveraged Large Language Models (LLMs) to generate programmatic policies for single-agent tasks, transforming neural network-based policies into interpretable rule-based code with high execution efficiency. Insp","authors_text":"Hangzhi Liu, Hongjie Zhang, Jie Ou, Mingrui Lv, Zhi Luo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T13:33:31Z","title":"PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06053","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":"sha256:1b475747b5fe87cdf487647ae93c0213eb3023b11f7633a3e831d0de1ebe0717","target":"record","created_at":"2026-07-05T12:06:29Z","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":"65d62ffef62172e062a86cdb2720a97363da05faa9afd209561d9fb0abc05233","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-07T13:33:31Z","title_canon_sha256":"a713b35b1c6064338003fac3b6335d0169a36e6de997835efb32e16da467f373"},"schema_version":"1.0","source":{"id":"2509.06053","kind":"arxiv","version":1}},"canonical_sha256":"4204bf82888cb45d3c65296f45ed4544768551e230b526f28cc56908834d7a64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4204bf82888cb45d3c65296f45ed4544768551e230b526f28cc56908834d7a64","first_computed_at":"2026-07-05T12:06:29.066785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:29.066785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V6b0yyk1ztrYaky0aob+ATvQOVyUeMB9P/LDh1OtdSE+bovqJNY5LibtdSaKpeimXkgZfn7qTS1mImI9FgbQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:29.067191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b475747b5fe87cdf487647ae93c0213eb3023b11f7633a3e831d0de1ebe0717","sha256:1e8c96d8e1bde5895755f30d84d903078bff4edf89f341b5f321997cef89d29d"],"state_sha256":"2db116cffaea22e4d5ac508ab6d32c0d811759a7c9cd21265436515e04fa018b"}