{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KLVSAKIZVKAH4PFP4JQYCU56D5","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":"6e610883b8268251ddc9b386f32a50a476ef96a32dade5c2e475b99fae397367","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T13:58:38Z","title_canon_sha256":"c58e8c773eff30f1e7f2cc237b5f1488991863360e87f7436fb7f5fcb06ef926"},"schema_version":"1.0","source":{"id":"2410.16024","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16024","created_at":"2026-07-05T10:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16024v3","created_at":"2026-07-05T10:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16024","created_at":"2026-07-05T10:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"KLVSAKIZVKAH","created_at":"2026-07-05T10:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"KLVSAKIZVKAH4PFP","created_at":"2026-07-05T10:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"KLVSAKIZ","created_at":"2026-07-05T10:25:12Z"}],"graph_snapshots":[{"event_id":"sha256:ffbced603a29daa72d9b99c0dd0fc46723b5b199a2807d98a7eb869ae0c44224","target":"graph","created_at":"2026-07-05T10:25:12Z","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/2410.16024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"StarCraft Multi-Agent Challenge (SMAC) has been one of the most commonly used experimental environments in multi-agent reinforcement learning (MARL), where the specific task is to control a set number of allied units to defeat enemy forces. Traditional MARL algorithms often require interacting with the environment for millions of steps to train a parametric model, of which the resulting policies are typically non-interpretable with weak transferability. In this paper, we introduce SMAC-R1 which is based on the Qwen2.5-7B-Base LLM distilled from DeepSeek-Coder-v2.5-236B. Similar to online reinf","authors_text":"Haifeng Zhang, Jian Zhao, Ruyi Song, Weiyu Ma, Yin Zhang, Yue Deng, Yuxin Fan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T13:58:38Z","title":"SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16024","kind":"arxiv","version":3},"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":"sha256:397c3f8f6b6f2242931ddbc5dd31f863806e78499c7cedf9ad57e83274d726e2","target":"record","created_at":"2026-07-05T10:25:12Z","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":"6e610883b8268251ddc9b386f32a50a476ef96a32dade5c2e475b99fae397367","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T13:58:38Z","title_canon_sha256":"c58e8c773eff30f1e7f2cc237b5f1488991863360e87f7436fb7f5fcb06ef926"},"schema_version":"1.0","source":{"id":"2410.16024","kind":"arxiv","version":3}},"canonical_sha256":"52eb202919aa807e3cafe2618153be1f5d313eb7a3720f37e4d09d96eeab20df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52eb202919aa807e3cafe2618153be1f5d313eb7a3720f37e4d09d96eeab20df","first_computed_at":"2026-07-05T10:25:12.403037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:12.403037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LTHVNlH/hLoP4Hp89Zgf3Ugleqb8AuudMBeelI5v7F2nCrT1pynLsCAzWD9F4uZ8ex/gxz2uOMcTa+AJ6oe+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:12.403543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16024","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:397c3f8f6b6f2242931ddbc5dd31f863806e78499c7cedf9ad57e83274d726e2","sha256:ffbced603a29daa72d9b99c0dd0fc46723b5b199a2807d98a7eb869ae0c44224"],"state_sha256":"e4b0c36f981c22057eb7dcae79202d44a43e9d24281f07c13e88055e54699d28"}