{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3NBG74IYG4Q3R2L4X3Q4FQWUFB","short_pith_number":"pith:3NBG74IY","canonical_record":{"source":{"id":"2407.01231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T12:22:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6fd209a92f435ab14ff4df391e3044c9fc94839a93c7b6a27d064092aa8b6cb3","abstract_canon_sha256":"e65fd2885ce8dcf34dc59ff83f8139c5e7bf28dfff15a3935d7e1c0fa55d1d1e"},"schema_version":"1.0"},"canonical_sha256":"db426ff1183721b8e97cbee1c2c2d42863f9f166500b64bdf3775244a41473ee","source":{"kind":"arxiv","id":"2407.01231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01231","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01231v1","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01231","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"3NBG74IYG4Q3","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"3NBG74IYG4Q3R2L4","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"3NBG74IY","created_at":"2026-07-05T08:38:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3NBG74IYG4Q3R2L4X3Q4FQWUFB","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T12:22:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6fd209a92f435ab14ff4df391e3044c9fc94839a93c7b6a27d064092aa8b6cb3","abstract_canon_sha256":"e65fd2885ce8dcf34dc59ff83f8139c5e7bf28dfff15a3935d7e1c0fa55d1d1e"},"schema_version":"1.0"},"canonical_sha256":"db426ff1183721b8e97cbee1c2c2d42863f9f166500b64bdf3775244a41473ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:44.898525Z","signature_b64":"oc/+A3zemGS26WLTvavI9FhjutOYudGpl3upksVJM8H7zgKNqZwWHWXBVg4+2LoWvWxto4uwsYtN3WcLl5BfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db426ff1183721b8e97cbee1c2c2d42863f9f166500b64bdf3775244a41473ee","last_reissued_at":"2026-07-05T08:38:44.898099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:44.898099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01231","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":"2026-07-05T08:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+tX6GQtBto4AX2fKwpj3N3oiaLhZEprZ9n9V8+jX+l5LHLY5riPV2TIaoRYgp33JfOHT6fu0e9PHMPisGtAFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:35:54.173834Z"},"content_sha256":"cb6b71aee00ec37a58a4b73fd708f6bca4ab3ed5e7c9ef69d5f5f58df10c09fe","schema_version":"1.0","event_id":"sha256:cb6b71aee00ec37a58a4b73fd708f6bca4ab3ed5e7c9ef69d5f5f58df10c09fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3NBG74IYG4Q3R2L4X3Q4FQWUFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIRAI: Evaluating LLM Agents for Event Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenchen Ye, Mingyu Derek Ma, Wei Wang, Yanqiao Zhu, Yihe Deng, Zijie Huang, Ziniu Hu","submitted_at":"2024-07-01T12:22:46Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have empowered LLM agents to autonomously collect world information, over which to conduct reasoning to solve complex problems. Given this capability, increasing interests have been put into employing LLM agents for predicting international events, which can influence decision-making and shape policy development on an international scale. Despite such a growing interest, there is a lack of a rigorous benchmark of LLM agents' forecasting capability and reliability. To address this gap, we introduce MIRAI, a novel benchmark designed to systemat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01231","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/2407.01231/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":"2026-07-05T08:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHBNkXIPQ7wOxqF67JhzUKRtSBLURGgjd4IUzzSOtjMPTyiLsvhR6p+iZ7YD2paA+vNCH5HY2ESUKBexIV9fCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:35:54.174405Z"},"content_sha256":"c609f95013824d892e92bbc8aeca8ebbb3f49b5e9baf4845fb1cfa2e9c2d141d","schema_version":"1.0","event_id":"sha256:c609f95013824d892e92bbc8aeca8ebbb3f49b5e9baf4845fb1cfa2e9c2d141d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NBG74IYG4Q3R2L4X3Q4FQWUFB/bundle.json","state_url":"https://pith.science/pith/3NBG74IYG4Q3R2L4X3Q4FQWUFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NBG74IYG4Q3R2L4X3Q4FQWUFB/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":"2026-08-23T06:35:54Z","links":{"resolver":"https://pith.science/pith/3NBG74IYG4Q3R2L4X3Q4FQWUFB","bundle":"https://pith.science/pith/3NBG74IYG4Q3R2L4X3Q4FQWUFB/bundle.json","state":"https://pith.science/pith/3NBG74IYG4Q3R2L4X3Q4FQWUFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NBG74IYG4Q3R2L4X3Q4FQWUFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3NBG74IYG4Q3R2L4X3Q4FQWUFB","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":"e65fd2885ce8dcf34dc59ff83f8139c5e7bf28dfff15a3935d7e1c0fa55d1d1e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T12:22:46Z","title_canon_sha256":"6fd209a92f435ab14ff4df391e3044c9fc94839a93c7b6a27d064092aa8b6cb3"},"schema_version":"1.0","source":{"id":"2407.01231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01231","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01231v1","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01231","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"3NBG74IYG4Q3","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"3NBG74IYG4Q3R2L4","created_at":"2026-07-05T08:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"3NBG74IY","created_at":"2026-07-05T08:38:44Z"}],"graph_snapshots":[{"event_id":"sha256:c609f95013824d892e92bbc8aeca8ebbb3f49b5e9baf4845fb1cfa2e9c2d141d","target":"graph","created_at":"2026-07-05T08:38:44Z","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/2407.01231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have empowered LLM agents to autonomously collect world information, over which to conduct reasoning to solve complex problems. Given this capability, increasing interests have been put into employing LLM agents for predicting international events, which can influence decision-making and shape policy development on an international scale. Despite such a growing interest, there is a lack of a rigorous benchmark of LLM agents' forecasting capability and reliability. To address this gap, we introduce MIRAI, a novel benchmark designed to systemat","authors_text":"Chenchen Ye, Mingyu Derek Ma, Wei Wang, Yanqiao Zhu, Yihe Deng, Zijie Huang, Ziniu Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T12:22:46Z","title":"MIRAI: Evaluating LLM Agents for Event Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01231","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:cb6b71aee00ec37a58a4b73fd708f6bca4ab3ed5e7c9ef69d5f5f58df10c09fe","target":"record","created_at":"2026-07-05T08:38:44Z","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":"e65fd2885ce8dcf34dc59ff83f8139c5e7bf28dfff15a3935d7e1c0fa55d1d1e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T12:22:46Z","title_canon_sha256":"6fd209a92f435ab14ff4df391e3044c9fc94839a93c7b6a27d064092aa8b6cb3"},"schema_version":"1.0","source":{"id":"2407.01231","kind":"arxiv","version":1}},"canonical_sha256":"db426ff1183721b8e97cbee1c2c2d42863f9f166500b64bdf3775244a41473ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db426ff1183721b8e97cbee1c2c2d42863f9f166500b64bdf3775244a41473ee","first_computed_at":"2026-07-05T08:38:44.898099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:44.898099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oc/+A3zemGS26WLTvavI9FhjutOYudGpl3upksVJM8H7zgKNqZwWHWXBVg4+2LoWvWxto4uwsYtN3WcLl5BfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:44.898525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb6b71aee00ec37a58a4b73fd708f6bca4ab3ed5e7c9ef69d5f5f58df10c09fe","sha256:c609f95013824d892e92bbc8aeca8ebbb3f49b5e9baf4845fb1cfa2e9c2d141d"],"state_sha256":"75bc61d08bd0d0725a9e4b52f4f458bb099a85bc89f1d49b714bdd91680734e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJLH/FXQQRp2GNAd2KhtcbVaOQcshmvKE5U6VKZHGPP+5c+SOERi65oZDmuop2FibYxh6nFKZ0H3PlYmpxi+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T06:35:54.178983Z","bundle_sha256":"023b7a9aae932df8fb29135cc336a94f4b6f603d0cacd9cc608f25a078e5b146"}}