{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZVY5V3WFZP5XC56NR7ITHJSD7V","short_pith_number":"pith:ZVY5V3WF","schema_version":"1.0","canonical_sha256":"cd71daeec5cbfb7177cd8fd133a643fd7b765cc8804bbe9b4dd59ede2ca78c55","source":{"kind":"arxiv","id":"2606.18950","version":2},"attestation_state":"computed","paper":{"title":"RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daechul Ahn, Hyeonbeom Choi, Jonghyun Choi, Reokyoung Kim, San Kim, Seungyeon Jwa","submitted_at":"2026-06-17T11:32:51Z","abstract_excerpt":"Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.e., anticipating and influencing other agents' actions, under uncertainty in competitive and cooperative settings. Real-time strategy (RTS) games can be a natural testbed for diagnosing this limitation, as they demand coordination with allies, adaptation to opponents' strategy, and long-horizon planning under partial observability. However, existing RTS benchmarks offer limited evaluation scope, lack systematic competency diagnosis, and remain fixed in the pre-designed scenario coverage. To address these limitation"},"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":"2606.18950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T11:32:51Z","cross_cats_sorted":[],"title_canon_sha256":"95c3983a990d0de1f48732314e2529a40393e167c90cfc12754279ed4774dd12","abstract_canon_sha256":"7f5ebe59a8a1b02996363b9c36a0af420a42b3906d9730749f1425adbaa783e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:22.309278Z","signature_b64":"WnpYVfpvTA+FNIQ1NfB6jg0zGy6vpVJ17GKbaGo9MR882/DE/7ZqtuVYLo+GoTzjH8y3GFdWIIRZ4sV2PVGJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd71daeec5cbfb7177cd8fd133a643fd7b765cc8804bbe9b4dd59ede2ca78c55","last_reissued_at":"2026-06-19T16:12:22.308937Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:22.308937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daechul Ahn, Hyeonbeom Choi, Jonghyun Choi, Reokyoung Kim, San Kim, Seungyeon Jwa","submitted_at":"2026-06-17T11:32:51Z","abstract_excerpt":"Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.e., anticipating and influencing other agents' actions, under uncertainty in competitive and cooperative settings. Real-time strategy (RTS) games can be a natural testbed for diagnosing this limitation, as they demand coordination with allies, adaptation to opponents' strategy, and long-horizon planning under partial observability. However, existing RTS benchmarks offer limited evaluation scope, lack systematic competency diagnosis, and remain fixed in the pre-designed scenario coverage. To address these limitation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18950","kind":"arxiv","version":2},"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/2606.18950/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":"2606.18950","created_at":"2026-06-19T16:12:22.308995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18950v2","created_at":"2026-06-19T16:12:22.308995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18950","created_at":"2026-06-19T16:12:22.308995+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVY5V3WFZP5X","created_at":"2026-06-19T16:12:22.308995+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVY5V3WFZP5XC56N","created_at":"2026-06-19T16:12:22.308995+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVY5V3WF","created_at":"2026-06-19T16:12:22.308995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V","json":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V.json","graph_json":"https://pith.science/api/pith-number/ZVY5V3WFZP5XC56NR7ITHJSD7V/graph.json","events_json":"https://pith.science/api/pith-number/ZVY5V3WFZP5XC56NR7ITHJSD7V/events.json","paper":"https://pith.science/paper/ZVY5V3WF"},"agent_actions":{"view_html":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V","download_json":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V.json","view_paper":"https://pith.science/paper/ZVY5V3WF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18950&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVY5V3WFZP5XC56NR7ITHJSD7V/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVY5V3WFZP5XC56NR7ITHJSD7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V/action/storage_attestation","attest_author":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V/action/author_attestation","sign_citation":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V/action/citation_signature","submit_replication":"https://pith.science/pith/ZVY5V3WFZP5XC56NR7ITHJSD7V/action/replication_record"}},"created_at":"2026-06-19T16:12:22.308995+00:00","updated_at":"2026-06-19T16:12:22.308995+00:00"}