{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XJ4JO6P5Z43E7FRPMH5GHQUJA2","short_pith_number":"pith:XJ4JO6P5","canonical_record":{"source":{"id":"2302.00093","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T20:48:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26a678251193c84a5eefb60b4fae1cd7d7cd92585b406851a9b975484b3e0fe7","abstract_canon_sha256":"511e9424022d3003e87eec45ae5beee0d7beadd66f2b9210359c4b55d7f75e89"},"schema_version":"1.0"},"canonical_sha256":"ba789779fdcf364f962f61fa63c28906a18675c47604ac39844e1540be93ed14","source":{"kind":"arxiv","id":"2302.00093","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00093","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00093v3","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00093","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"XJ4JO6P5Z43E","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"XJ4JO6P5Z43E7FRP","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"XJ4JO6P5","created_at":"2026-07-05T06:17:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XJ4JO6P5Z43E7FRPMH5GHQUJA2","target":"record","payload":{"canonical_record":{"source":{"id":"2302.00093","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T20:48:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26a678251193c84a5eefb60b4fae1cd7d7cd92585b406851a9b975484b3e0fe7","abstract_canon_sha256":"511e9424022d3003e87eec45ae5beee0d7beadd66f2b9210359c4b55d7f75e89"},"schema_version":"1.0"},"canonical_sha256":"ba789779fdcf364f962f61fa63c28906a18675c47604ac39844e1540be93ed14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:45.622947Z","signature_b64":"+xkrJmwIi5ZpYuzfHIOmkYIiqTcl30dZ0SzaBea7bhtWgYFrzK0ph9AHPKI5zAzg4oDsTZZUPKHmsS3Pif4eBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba789779fdcf364f962f61fa63c28906a18675c47604ac39844e1540be93ed14","last_reissued_at":"2026-07-05T06:17:45.622337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:45.622337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.00093","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDcpoT4QgjpARDtgjGfl0bwkBz29gIn+9qd1liMukyBxXhTy3FU26c6kixS8KmPviSncrDqQKrn9R5Nx00aBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:10:29.101700Z"},"content_sha256":"b8c04877dfa70c6c04c2c58ab54c3eb5fd2a2c35f2bb7c2ea930421b7d34c7ef","schema_version":"1.0","event_id":"sha256:b8c04877dfa70c6c04c2c58ab54c3eb5fd2a2c35f2bb7c2ea930421b7d34c7ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XJ4JO6P5Z43E7FRPMH5GHQUJA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Dohan, Denny Zhou, Ed Chi, Freda Shi, Kanishka Misra, Nathanael Sch\\\"arli, Nathan Scales, Xinyun Chen","submitted_at":"2023-01-31T20:48:57Z","abstract_excerpt":"Large language models have achieved impressive performance on various natural language processing tasks. However, so far they have been evaluated primarily on benchmarks where all information in the input context is relevant for solving the task. In this work, we investigate the distractibility of large language models, i.e., how the model problem-solving accuracy can be influenced by irrelevant context. In particular, we introduce Grade-School Math with Irrelevant Context (GSM-IC), an arithmetic reasoning dataset with irrelevant information in the problem description. We use this benchmark to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00093","kind":"arxiv","version":3},"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/2302.00093/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":"2026-07-05T06:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RbFFIJZFtILzNXQlTwH6FEwwaGVGXgcMRT1zr7/g2BEZwKcb7kSp7LoAl3fY3MbUFZkcSqeZJ39J7mIU7jjICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:10:29.102207Z"},"content_sha256":"b2d53b68a2c463a1353adffaf2e3b813ad4c9ca950105b0a8fefb0c5255f2768","schema_version":"1.0","event_id":"sha256:b2d53b68a2c463a1353adffaf2e3b813ad4c9ca950105b0a8fefb0c5255f2768"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJ4JO6P5Z43E7FRPMH5GHQUJA2/bundle.json","state_url":"https://pith.science/pith/XJ4JO6P5Z43E7FRPMH5GHQUJA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJ4JO6P5Z43E7FRPMH5GHQUJA2/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":"2026-08-17T19:10:29Z","links":{"resolver":"https://pith.science/pith/XJ4JO6P5Z43E7FRPMH5GHQUJA2","bundle":"https://pith.science/pith/XJ4JO6P5Z43E7FRPMH5GHQUJA2/bundle.json","state":"https://pith.science/pith/XJ4JO6P5Z43E7FRPMH5GHQUJA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJ4JO6P5Z43E7FRPMH5GHQUJA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XJ4JO6P5Z43E7FRPMH5GHQUJA2","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":"511e9424022d3003e87eec45ae5beee0d7beadd66f2b9210359c4b55d7f75e89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T20:48:57Z","title_canon_sha256":"26a678251193c84a5eefb60b4fae1cd7d7cd92585b406851a9b975484b3e0fe7"},"schema_version":"1.0","source":{"id":"2302.00093","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00093","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00093v3","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00093","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"XJ4JO6P5Z43E","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"XJ4JO6P5Z43E7FRP","created_at":"2026-07-05T06:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"XJ4JO6P5","created_at":"2026-07-05T06:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:b2d53b68a2c463a1353adffaf2e3b813ad4c9ca950105b0a8fefb0c5255f2768","target":"graph","created_at":"2026-07-05T06:17:45Z","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/2302.00093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have achieved impressive performance on various natural language processing tasks. However, so far they have been evaluated primarily on benchmarks where all information in the input context is relevant for solving the task. In this work, we investigate the distractibility of large language models, i.e., how the model problem-solving accuracy can be influenced by irrelevant context. In particular, we introduce Grade-School Math with Irrelevant Context (GSM-IC), an arithmetic reasoning dataset with irrelevant information in the problem description. We use this benchmark to","authors_text":"David Dohan, Denny Zhou, Ed Chi, Freda Shi, Kanishka Misra, Nathanael Sch\\\"arli, Nathan Scales, Xinyun Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T20:48:57Z","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00093","kind":"arxiv","version":3},"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:b8c04877dfa70c6c04c2c58ab54c3eb5fd2a2c35f2bb7c2ea930421b7d34c7ef","target":"record","created_at":"2026-07-05T06:17:45Z","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":"511e9424022d3003e87eec45ae5beee0d7beadd66f2b9210359c4b55d7f75e89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T20:48:57Z","title_canon_sha256":"26a678251193c84a5eefb60b4fae1cd7d7cd92585b406851a9b975484b3e0fe7"},"schema_version":"1.0","source":{"id":"2302.00093","kind":"arxiv","version":3}},"canonical_sha256":"ba789779fdcf364f962f61fa63c28906a18675c47604ac39844e1540be93ed14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba789779fdcf364f962f61fa63c28906a18675c47604ac39844e1540be93ed14","first_computed_at":"2026-07-05T06:17:45.622337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:45.622337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+xkrJmwIi5ZpYuzfHIOmkYIiqTcl30dZ0SzaBea7bhtWgYFrzK0ph9AHPKI5zAzg4oDsTZZUPKHmsS3Pif4eBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:45.622947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.00093","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8c04877dfa70c6c04c2c58ab54c3eb5fd2a2c35f2bb7c2ea930421b7d34c7ef","sha256:b2d53b68a2c463a1353adffaf2e3b813ad4c9ca950105b0a8fefb0c5255f2768"],"state_sha256":"6323267c852c4baca403d505b817870aafa31dcb54adf4f869ab6b63217c57f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuA7bBvRx/p6XXHf/cTPvrdhBCzBPMp+5/RnCaCeuHyHOBov4Hing4QVL5eTKvTYGFNpXA1e8Qwtl+J/bDamDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T19:10:29.107372Z","bundle_sha256":"c3558d3c58552e98ecd123fb365d36e501b972f7f8a56decf7eb3976572631c2"}}