{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IPBCX2E2HBHBIVXWKC7JOR7IXC","short_pith_number":"pith:IPBCX2E2","canonical_record":{"source":{"id":"2605.22238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T09:41:16Z","cross_cats_sorted":[],"title_canon_sha256":"7f0f0c487abd46bd78314a352075f06768faba3823eb39dd987a6e8f0394ce78","abstract_canon_sha256":"04c05c7c19d04a59bdbda8aedd26527cdbaf8307d2e7a3e290d0da6cf953881e"},"schema_version":"1.0"},"canonical_sha256":"43c22be89a384e1456f650be9747e8b89c1fc7079f83acf36c5f4a540211047f","source":{"kind":"arxiv","id":"2605.22238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22238","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22238v1","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22238","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"IPBCX2E2HBHB","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"IPBCX2E2HBHBIVXW","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"IPBCX2E2","created_at":"2026-05-22T01:04:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IPBCX2E2HBHBIVXWKC7JOR7IXC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T09:41:16Z","cross_cats_sorted":[],"title_canon_sha256":"7f0f0c487abd46bd78314a352075f06768faba3823eb39dd987a6e8f0394ce78","abstract_canon_sha256":"04c05c7c19d04a59bdbda8aedd26527cdbaf8307d2e7a3e290d0da6cf953881e"},"schema_version":"1.0"},"canonical_sha256":"43c22be89a384e1456f650be9747e8b89c1fc7079f83acf36c5f4a540211047f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:33.736355Z","signature_b64":"4W6Jhf35Rf5M32T3wygn8Asjy17F5F2wLS4keNzsda4pSVuwYOwCUyqGVECFa8f49jGtEiaMx92FGP6HOmg3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43c22be89a384e1456f650be9747e8b89c1fc7079f83acf36c5f4a540211047f","last_reissued_at":"2026-05-22T01:04:33.735588Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:33.735588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22238","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AKVDSol7KzwtyJNPm+ee6cOaXylvDvH4uBgSK7toZ2IZQ0KH0anudjq5OnvkQBPtmtFop1eMGBW6oqK4q/B3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:45:36.494777Z"},"content_sha256":"0a31f054427af08aede1a876de377c91d612e9756577efd2909675aee56cf4c3","schema_version":"1.0","event_id":"sha256:0a31f054427af08aede1a876de377c91d612e9756577efd2909675aee56cf4c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IPBCX2E2HBHBIVXWKC7JOR7IXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"H. C. Ekne","submitted_at":"2026-05-21T09:41:16Z","abstract_excerpt":"Static benchmarks capture only part of how large language models behave in practice. Real systems place models inside repeated loops with time limits, formatting constraints, and failure modes. We study this setting in a timed multi-phase Risk environment with explicit victory targets and repeated planning and execution cycles. In a replicated 32-game cross-provider championship under frozen rules, gemini-3.1-pro-preview won 20 of 32 games against gpt-5.1, claude-opus-4-7, and kimi-k2.6, and the pooled winner distribution differs strongly from an equal-strength null (p approx 1.5 x 10^-5). We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22238","kind":"arxiv","version":1},"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/2605.22238/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EKaeUD739cvSSArc5ZuxTml1ruAmJTIYJ0PBSzuSvLnV0HqePWRnltGZEJ2DQVdp29GdM6IVT27ZSw/t6cD4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:45:36.495155Z"},"content_sha256":"109679cd9ca8c124893d919f3ac93947fa975b4f650bc55c5c8f74e45c2be732","schema_version":"1.0","event_id":"sha256:109679cd9ca8c124893d919f3ac93947fa975b4f650bc55c5c8f74e45c2be732"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IPBCX2E2HBHBIVXWKC7JOR7IXC/bundle.json","state_url":"https://pith.science/pith/IPBCX2E2HBHBIVXWKC7JOR7IXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IPBCX2E2HBHBIVXWKC7JOR7IXC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T21:45:36Z","links":{"resolver":"https://pith.science/pith/IPBCX2E2HBHBIVXWKC7JOR7IXC","bundle":"https://pith.science/pith/IPBCX2E2HBHBIVXWKC7JOR7IXC/bundle.json","state":"https://pith.science/pith/IPBCX2E2HBHBIVXWKC7JOR7IXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IPBCX2E2HBHBIVXWKC7JOR7IXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IPBCX2E2HBHBIVXWKC7JOR7IXC","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":"04c05c7c19d04a59bdbda8aedd26527cdbaf8307d2e7a3e290d0da6cf953881e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T09:41:16Z","title_canon_sha256":"7f0f0c487abd46bd78314a352075f06768faba3823eb39dd987a6e8f0394ce78"},"schema_version":"1.0","source":{"id":"2605.22238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22238","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22238v1","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22238","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"IPBCX2E2HBHB","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"IPBCX2E2HBHBIVXW","created_at":"2026-05-22T01:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"IPBCX2E2","created_at":"2026-05-22T01:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:109679cd9ca8c124893d919f3ac93947fa975b4f650bc55c5c8f74e45c2be732","target":"graph","created_at":"2026-05-22T01:04:33Z","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/2605.22238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Static benchmarks capture only part of how large language models behave in practice. Real systems place models inside repeated loops with time limits, formatting constraints, and failure modes. We study this setting in a timed multi-phase Risk environment with explicit victory targets and repeated planning and execution cycles. In a replicated 32-game cross-provider championship under frozen rules, gemini-3.1-pro-preview won 20 of 32 games against gpt-5.1, claude-opus-4-7, and kimi-k2.6, and the pooled winner distribution differs strongly from an equal-strength null (p approx 1.5 x 10^-5). We ","authors_text":"H. C. Ekne","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T09:41:16Z","title":"Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22238","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":"sha256:0a31f054427af08aede1a876de377c91d612e9756577efd2909675aee56cf4c3","target":"record","created_at":"2026-05-22T01:04:33Z","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":"04c05c7c19d04a59bdbda8aedd26527cdbaf8307d2e7a3e290d0da6cf953881e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T09:41:16Z","title_canon_sha256":"7f0f0c487abd46bd78314a352075f06768faba3823eb39dd987a6e8f0394ce78"},"schema_version":"1.0","source":{"id":"2605.22238","kind":"arxiv","version":1}},"canonical_sha256":"43c22be89a384e1456f650be9747e8b89c1fc7079f83acf36c5f4a540211047f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43c22be89a384e1456f650be9747e8b89c1fc7079f83acf36c5f4a540211047f","first_computed_at":"2026-05-22T01:04:33.735588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:33.735588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4W6Jhf35Rf5M32T3wygn8Asjy17F5F2wLS4keNzsda4pSVuwYOwCUyqGVECFa8f49jGtEiaMx92FGP6HOmg3Bg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:33.736355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a31f054427af08aede1a876de377c91d612e9756577efd2909675aee56cf4c3","sha256:109679cd9ca8c124893d919f3ac93947fa975b4f650bc55c5c8f74e45c2be732"],"state_sha256":"f1468d7132741fd076f9f5096bc2ae3979ecfb0ec61dc4eb30b9d3a26731e692"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YbbfbtFyHTiddqEfn4lKkanToKlXuQDsiHCilSsdS5INAt77wao/DAAoppN5QL309FCHIRGO/9YPXiYCqEjBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T21:45:36.497182Z","bundle_sha256":"a2e445c5cde27eccf509b9648e18a1216b990e4721adb54ab8d02042784e4e4b"}}