{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLVSAKIZVKAH4PFP4JQYCU56D5","short_pith_number":"pith:KLVSAKIZ","schema_version":"1.0","canonical_sha256":"52eb202919aa807e3cafe2618153be1f5d313eb7a3720f37e4d09d96eeab20df","source":{"kind":"arxiv","id":"2410.16024","version":3},"attestation_state":"computed","paper":{"title":"SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haifeng Zhang, Jian Zhao, Ruyi Song, Weiyu Ma, Yin Zhang, Yue Deng, Yuxin Fan","submitted_at":"2024-10-21T13:58:38Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.16024","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T13:58:38Z","cross_cats_sorted":[],"title_canon_sha256":"c58e8c773eff30f1e7f2cc237b5f1488991863360e87f7436fb7f5fcb06ef926","abstract_canon_sha256":"6e610883b8268251ddc9b386f32a50a476ef96a32dade5c2e475b99fae397367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:12.403543Z","signature_b64":"LTHVNlH/hLoP4Hp89Zgf3Ugleqb8AuudMBeelI5v7F2nCrT1pynLsCAzWD9F4uZ8ex/gxz2uOMcTa+AJ6oe+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52eb202919aa807e3cafe2618153be1f5d313eb7a3720f37e4d09d96eeab20df","last_reissued_at":"2026-07-05T10:25:12.403037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:12.403037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haifeng Zhang, Jian Zhao, Ruyi Song, Weiyu Ma, Yin Zhang, Yue Deng, Yuxin Fan","submitted_at":"2024-10-21T13:58:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16024","kind":"arxiv","version":3},"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/2410.16024/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.16024","created_at":"2026-07-05T10:25:12.403098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16024v3","created_at":"2026-07-05T10:25:12.403098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16024","created_at":"2026-07-05T10:25:12.403098+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLVSAKIZVKAH","created_at":"2026-07-05T10:25:12.403098+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLVSAKIZVKAH4PFP","created_at":"2026-07-05T10:25:12.403098+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLVSAKIZ","created_at":"2026-07-05T10:25:12.403098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09586","citing_title":"EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5","json":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5.json","graph_json":"https://pith.science/api/pith-number/KLVSAKIZVKAH4PFP4JQYCU56D5/graph.json","events_json":"https://pith.science/api/pith-number/KLVSAKIZVKAH4PFP4JQYCU56D5/events.json","paper":"https://pith.science/paper/KLVSAKIZ"},"agent_actions":{"view_html":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5","download_json":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5.json","view_paper":"https://pith.science/paper/KLVSAKIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16024&json=true","fetch_graph":"https://pith.science/api/pith-number/KLVSAKIZVKAH4PFP4JQYCU56D5/graph.json","fetch_events":"https://pith.science/api/pith-number/KLVSAKIZVKAH4PFP4JQYCU56D5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5/action/storage_attestation","attest_author":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5/action/author_attestation","sign_citation":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5/action/citation_signature","submit_replication":"https://pith.science/pith/KLVSAKIZVKAH4PFP4JQYCU56D5/action/replication_record"}},"created_at":"2026-07-05T10:25:12.403098+00:00","updated_at":"2026-07-05T10:25:12.403098+00:00"}