{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZEM7HUKEYPNVMFRYGG2I4QV7SV","short_pith_number":"pith:ZEM7HUKE","canonical_record":{"source":{"id":"2605.29512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T07:33:47Z","cross_cats_sorted":[],"title_canon_sha256":"a6be3168a61ae2e63503561de74c9b057731310103af3c7c332bb477530f18f8","abstract_canon_sha256":"0b9d799ba594cd2cfe471a4634859c0067cac5789e7741be130dc3d433245653"},"schema_version":"1.0"},"canonical_sha256":"c919f3d144c3db56163831b48e42bf95610d2d855585c9d9cd1aac08ae873e13","source":{"kind":"arxiv","id":"2605.29512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29512","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29512v1","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29512","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZEM7HUKEYPNV","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZEM7HUKEYPNVMFRY","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZEM7HUKE","created_at":"2026-05-29T01:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZEM7HUKEYPNVMFRYGG2I4QV7SV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T07:33:47Z","cross_cats_sorted":[],"title_canon_sha256":"a6be3168a61ae2e63503561de74c9b057731310103af3c7c332bb477530f18f8","abstract_canon_sha256":"0b9d799ba594cd2cfe471a4634859c0067cac5789e7741be130dc3d433245653"},"schema_version":"1.0"},"canonical_sha256":"c919f3d144c3db56163831b48e42bf95610d2d855585c9d9cd1aac08ae873e13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:44.264551Z","signature_b64":"0Fdkiv54jzogq8pwex6guzMWPM0isbyCkorvQPIOBXXwBIfhfA26HbB3v2MdbLdFQcxQOWI6u9iFr8MGTOFvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c919f3d144c3db56163831b48e42bf95610d2d855585c9d9cd1aac08ae873e13","last_reissued_at":"2026-05-29T01:05:44.263985Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:44.263985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29512","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":"2026-05-29T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGdGu8w2iF4nvss2ALKydlR5Dl3e0nmXFqTRhaJelXvomXR2FHRu49Cu82/vsZd43W+qqjTFLl6x7CQ+yYqFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:52:07.352358Z"},"content_sha256":"2acc8f340fbec4ce21cc2307bebb5e4c13479df07a8feb1796333e2e724abe1b","schema_version":"1.0","event_id":"sha256:2acc8f340fbec4ce21cc2307bebb5e4c13479df07a8feb1796333e2e724abe1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZEM7HUKEYPNVMFRYGG2I4QV7SV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aditya Ranjan, Alexander Buyantuev, Aliaksei Korshuk, Amol Bandagale, Anna Th\\\"oni, Aravind S, Arvin Chung, Atlas Wang, Avinash Anish, Benjamin Finch, Benjamin Kempinski, Bobby Cheng, Cheston Tan, ChunEn Hsiao, Govind Arun, Hao Liao, Hongkun Yao, I-Chen Wu, I-Hsuan Chu, Ilya Makarov, Jerry John Thomas, Jianzhu Yao, Jingxuan Fu, Jiwei Zhang, Kevin Wang, Kirtana Sunil Phatnani, Leon Guertler, Leshem Choshen, Maria Polukarov, Mathieu Lauri\\`ere, Mihir S Arya, Mossimo Ebeling, Nikhil Arora, Paval KS, Pramod Viswanath, Qinlu Cao, Sadhvik Bathini, Siyuan Wu, Tal Kachman, Tanya Upadhyay, Ti-Rong Wu, Viraj Nadkarni, Vrushali Mehta, Yan-Ru Ju, Yihan Jiang, Yiheng Sun, Yitian Huang, Yoram Bachrach, Yuan Lu, Yu-Chi Cheng, Yuhong Dai, YuTing Lin, Yu-Yu Yang","submitted_at":"2026-05-28T07:33:47Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended interaction remains poorly understood. Existing evaluations rely on static vignettes or single-game benchmarks that cannot capture the sustained, multi-faceted reasoning that real-world multi-agent settings demand. We introduce Mindgames, a multi-game arena and evaluation platform for LLM agents that operationalizes complementary reasoning demands relevant to ``theory of mind'': belief attribution under hidden information, opponent modeling through r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29512","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/2605.29512/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":"2026-05-29T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqkCzGJFJ+xAVKksmI8CWI3OBbPQqNrfsAz4is1uT2vjJuitUEIvleB19BAmDsqnwSpNx1N4SQRleqIl5pDmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:52:07.353079Z"},"content_sha256":"7cc70521a47ca6dcfb3066f30116efb7f13c6dbe5eac11ed0cca9ecf1291d5de","schema_version":"1.0","event_id":"sha256:7cc70521a47ca6dcfb3066f30116efb7f13c6dbe5eac11ed0cca9ecf1291d5de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEM7HUKEYPNVMFRYGG2I4QV7SV/bundle.json","state_url":"https://pith.science/pith/ZEM7HUKEYPNVMFRYGG2I4QV7SV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEM7HUKEYPNVMFRYGG2I4QV7SV/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":"2026-05-31T11:52:07Z","links":{"resolver":"https://pith.science/pith/ZEM7HUKEYPNVMFRYGG2I4QV7SV","bundle":"https://pith.science/pith/ZEM7HUKEYPNVMFRYGG2I4QV7SV/bundle.json","state":"https://pith.science/pith/ZEM7HUKEYPNVMFRYGG2I4QV7SV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEM7HUKEYPNVMFRYGG2I4QV7SV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZEM7HUKEYPNVMFRYGG2I4QV7SV","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":"0b9d799ba594cd2cfe471a4634859c0067cac5789e7741be130dc3d433245653","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T07:33:47Z","title_canon_sha256":"a6be3168a61ae2e63503561de74c9b057731310103af3c7c332bb477530f18f8"},"schema_version":"1.0","source":{"id":"2605.29512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29512","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29512v1","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29512","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZEM7HUKEYPNV","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZEM7HUKEYPNVMFRY","created_at":"2026-05-29T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZEM7HUKE","created_at":"2026-05-29T01:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:7cc70521a47ca6dcfb3066f30116efb7f13c6dbe5eac11ed0cca9ecf1291d5de","target":"graph","created_at":"2026-05-29T01:05:44Z","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/2605.29512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended interaction remains poorly understood. Existing evaluations rely on static vignettes or single-game benchmarks that cannot capture the sustained, multi-faceted reasoning that real-world multi-agent settings demand. We introduce Mindgames, a multi-game arena and evaluation platform for LLM agents that operationalizes complementary reasoning demands relevant to ``theory of mind'': belief attribution under hidden information, opponent modeling through r","authors_text":"Aditya Ranjan, Alexander Buyantuev, Aliaksei Korshuk, Amol Bandagale, Anna Th\\\"oni, Aravind S, Arvin Chung, Atlas Wang, Avinash Anish, Benjamin Finch, Benjamin Kempinski, Bobby Cheng, Cheston Tan, ChunEn Hsiao, Govind Arun, Hao Liao, Hongkun Yao, I-Chen Wu, I-Hsuan Chu, Ilya Makarov, Jerry John Thomas, Jianzhu Yao, Jingxuan Fu, Jiwei Zhang, Kevin Wang, Kirtana Sunil Phatnani, Leon Guertler, Leshem Choshen, Maria Polukarov, Mathieu Lauri\\`ere, Mihir S Arya, Mossimo Ebeling, Nikhil Arora, Paval KS, Pramod Viswanath, Qinlu Cao, Sadhvik Bathini, Siyuan Wu, Tal Kachman, Tanya Upadhyay, Ti-Rong Wu, Viraj Nadkarni, Vrushali Mehta, Yan-Ru Ju, Yihan Jiang, Yiheng Sun, Yitian Huang, Yoram Bachrach, Yuan Lu, Yu-Chi Cheng, Yuhong Dai, YuTing Lin, Yu-Yu Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T07:33:47Z","title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29512","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":"sha256:2acc8f340fbec4ce21cc2307bebb5e4c13479df07a8feb1796333e2e724abe1b","target":"record","created_at":"2026-05-29T01:05:44Z","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":"0b9d799ba594cd2cfe471a4634859c0067cac5789e7741be130dc3d433245653","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T07:33:47Z","title_canon_sha256":"a6be3168a61ae2e63503561de74c9b057731310103af3c7c332bb477530f18f8"},"schema_version":"1.0","source":{"id":"2605.29512","kind":"arxiv","version":1}},"canonical_sha256":"c919f3d144c3db56163831b48e42bf95610d2d855585c9d9cd1aac08ae873e13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c919f3d144c3db56163831b48e42bf95610d2d855585c9d9cd1aac08ae873e13","first_computed_at":"2026-05-29T01:05:44.263985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:44.263985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Fdkiv54jzogq8pwex6guzMWPM0isbyCkorvQPIOBXXwBIfhfA26HbB3v2MdbLdFQcxQOWI6u9iFr8MGTOFvAA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:44.264551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2acc8f340fbec4ce21cc2307bebb5e4c13479df07a8feb1796333e2e724abe1b","sha256:7cc70521a47ca6dcfb3066f30116efb7f13c6dbe5eac11ed0cca9ecf1291d5de"],"state_sha256":"7fae75b49a6302da28255d916e83ec4d53e6e2feedc0adf11d51b619a914684c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A8nnPr3jZCVjuVrYChB/AroAq7weKtah3H28pPxVW9zHfwzs6TkoUeZkBET2mL0lp5o/+cBPfpkSVTOVIzAbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T11:52:07.356862Z","bundle_sha256":"54a75661d873a5ff7d74b0a4879722ea48e2e8957e113d6eb9ccae08b333a4f0"}}