{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z7K6SKAQZSJYYY6SNUNGASRXYD","short_pith_number":"pith:Z7K6SKAQ","canonical_record":{"source":{"id":"2406.09170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:31:19Z","cross_cats_sorted":[],"title_canon_sha256":"a70e9e050823467428c06dd624f779011b03056cbf64d7bb3482df3c1d0e7ac5","abstract_canon_sha256":"63cd8f7c22b589fb13356b5ebf6eddc8c2c385669538424fb8abd9430a9e8641"},"schema_version":"1.0"},"canonical_sha256":"cfd5e92810cc938c63d26d1a604a37c0fcc9534c6252cacff5a65e72cb52665f","source":{"kind":"arxiv","id":"2406.09170","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09170","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09170v1","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09170","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"Z7K6SKAQZSJY","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"Z7K6SKAQZSJYYY6S","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"Z7K6SKAQ","created_at":"2026-07-05T08:31:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z7K6SKAQZSJYYY6SNUNGASRXYD","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:31:19Z","cross_cats_sorted":[],"title_canon_sha256":"a70e9e050823467428c06dd624f779011b03056cbf64d7bb3482df3c1d0e7ac5","abstract_canon_sha256":"63cd8f7c22b589fb13356b5ebf6eddc8c2c385669538424fb8abd9430a9e8641"},"schema_version":"1.0"},"canonical_sha256":"cfd5e92810cc938c63d26d1a604a37c0fcc9534c6252cacff5a65e72cb52665f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:29.478368Z","signature_b64":"p1Jn0ggGYyq6YvOtGX8ttZGM1Jt11wSwUym9u/CqgwaLFUk6TKB8RcxDq2TPtM0KsppGBMk6Cob0TVjGCo6uBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfd5e92810cc938c63d26d1a604a37c0fcc9534c6252cacff5a65e72cb52665f","last_reissued_at":"2026-07-05T08:31:29.477846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:29.477846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09170","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":"2026-07-05T08:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TXigVun9qsVDWbWVBAjXnIRjKyuJ0orEawUW5gbOxT53DbzNcVNzNgsjHtDuv4MEZhwxlmSMxK3DckuJU4v3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:13:25.726422Z"},"content_sha256":"f562a92791baba15f786e0a5e8f4c36130a54b6cccf0a43f6fbe99b149945b40","schema_version":"1.0","event_id":"sha256:f562a92791baba15f786e0a5e8f4c36130a54b6cccf0a43f6fbe99b149945b40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z7K6SKAQZSJYYY6SNUNGASRXYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anton Tsitsulin, Bahare Fatemi, Bryan Perozzi, Jinyeong Yim, John Palowitch, Jonathan Halcrow, Karishma Malkan, Mehran Kazemi, Sungyong Seo","submitted_at":"2024-06-13T14:31:19Z","abstract_excerpt":"Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors, particularly in temporal reasoning tasks involving complex temporal logic. Existing research has explored LLM performance on temporal reasoning using diverse datasets and benchmarks. However, these studies often rely on real-world data that LLMs may have encountered during pre-training or employ anonymization techniques that can inadvertently introduce factual inconsistencies. In this work, we address these limitations by introducing novel synthetic datasets specifically design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09170","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/2406.09170/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":"2026-07-05T08:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KLT8wWmPQxEXQdR0LJb7idK7j7+D0jI54/salyUxP+HkbKyM70j1vvaAQb3PS42puZdZStHJIa2luArSIK+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:13:25.726912Z"},"content_sha256":"0b90c10d2d236aa9363b939386a7eec00106dd5aef434989838c5592a6a5e400","schema_version":"1.0","event_id":"sha256:0b90c10d2d236aa9363b939386a7eec00106dd5aef434989838c5592a6a5e400"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z7K6SKAQZSJYYY6SNUNGASRXYD/bundle.json","state_url":"https://pith.science/pith/Z7K6SKAQZSJYYY6SNUNGASRXYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z7K6SKAQZSJYYY6SNUNGASRXYD/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":"2026-08-09T20:13:25Z","links":{"resolver":"https://pith.science/pith/Z7K6SKAQZSJYYY6SNUNGASRXYD","bundle":"https://pith.science/pith/Z7K6SKAQZSJYYY6SNUNGASRXYD/bundle.json","state":"https://pith.science/pith/Z7K6SKAQZSJYYY6SNUNGASRXYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z7K6SKAQZSJYYY6SNUNGASRXYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z7K6SKAQZSJYYY6SNUNGASRXYD","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":"63cd8f7c22b589fb13356b5ebf6eddc8c2c385669538424fb8abd9430a9e8641","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:31:19Z","title_canon_sha256":"a70e9e050823467428c06dd624f779011b03056cbf64d7bb3482df3c1d0e7ac5"},"schema_version":"1.0","source":{"id":"2406.09170","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09170","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09170v1","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09170","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"Z7K6SKAQZSJY","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"Z7K6SKAQZSJYYY6S","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"Z7K6SKAQ","created_at":"2026-07-05T08:31:29Z"}],"graph_snapshots":[{"event_id":"sha256:0b90c10d2d236aa9363b939386a7eec00106dd5aef434989838c5592a6a5e400","target":"graph","created_at":"2026-07-05T08:31:29Z","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/2406.09170/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors, particularly in temporal reasoning tasks involving complex temporal logic. Existing research has explored LLM performance on temporal reasoning using diverse datasets and benchmarks. However, these studies often rely on real-world data that LLMs may have encountered during pre-training or employ anonymization techniques that can inadvertently introduce factual inconsistencies. In this work, we address these limitations by introducing novel synthetic datasets specifically design","authors_text":"Anton Tsitsulin, Bahare Fatemi, Bryan Perozzi, Jinyeong Yim, John Palowitch, Jonathan Halcrow, Karishma Malkan, Mehran Kazemi, Sungyong Seo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:31:19Z","title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09170","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:f562a92791baba15f786e0a5e8f4c36130a54b6cccf0a43f6fbe99b149945b40","target":"record","created_at":"2026-07-05T08:31:29Z","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":"63cd8f7c22b589fb13356b5ebf6eddc8c2c385669538424fb8abd9430a9e8641","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:31:19Z","title_canon_sha256":"a70e9e050823467428c06dd624f779011b03056cbf64d7bb3482df3c1d0e7ac5"},"schema_version":"1.0","source":{"id":"2406.09170","kind":"arxiv","version":1}},"canonical_sha256":"cfd5e92810cc938c63d26d1a604a37c0fcc9534c6252cacff5a65e72cb52665f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfd5e92810cc938c63d26d1a604a37c0fcc9534c6252cacff5a65e72cb52665f","first_computed_at":"2026-07-05T08:31:29.477846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:29.477846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p1Jn0ggGYyq6YvOtGX8ttZGM1Jt11wSwUym9u/CqgwaLFUk6TKB8RcxDq2TPtM0KsppGBMk6Cob0TVjGCo6uBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:29.478368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09170","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f562a92791baba15f786e0a5e8f4c36130a54b6cccf0a43f6fbe99b149945b40","sha256:0b90c10d2d236aa9363b939386a7eec00106dd5aef434989838c5592a6a5e400"],"state_sha256":"066c0820195fc60b1899d522fbd1dc1ff5b4efa9682e7664783d31ba6bc8f069"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBuvWZIAe8Vif04gSN4KAfr2ludM9yyPVT6sbdjFdVBwiDOz+uHnUGZlJYhqIEIT5Thv+wgQaz1N/GfCFwauDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:13:25.730453Z","bundle_sha256":"4a3a707f03d09d0bb28bd3927fd99c31c7b97e1f28067b0f79f70318bc582e4c"}}