{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L6DVLFH6QKIWIGB7R7CPWUXCFV","short_pith_number":"pith:L6DVLFH6","canonical_record":{"source":{"id":"2402.08939","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T04:50:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a01f4cce52ba2285d96b23396284fb31c8534d7f322ffb897956b57687ad02b5","abstract_canon_sha256":"654701d4e58c0507d9184e948dad726d351f36869d2390268207012df903bc7d"},"schema_version":"1.0"},"canonical_sha256":"5f875594fe829164183f8fc4fb52e22d7b29f29eb0955ca7b1ee4b0c67e5fb8a","source":{"kind":"arxiv","id":"2402.08939","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08939","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08939v3","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08939","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"L6DVLFH6QKIW","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"L6DVLFH6QKIWIGB7","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"L6DVLFH6","created_at":"2026-07-05T08:24:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L6DVLFH6QKIWIGB7R7CPWUXCFV","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08939","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T04:50:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a01f4cce52ba2285d96b23396284fb31c8534d7f322ffb897956b57687ad02b5","abstract_canon_sha256":"654701d4e58c0507d9184e948dad726d351f36869d2390268207012df903bc7d"},"schema_version":"1.0"},"canonical_sha256":"5f875594fe829164183f8fc4fb52e22d7b29f29eb0955ca7b1ee4b0c67e5fb8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:01.583236Z","signature_b64":"a/Bil8IA0J165vmTnIJ8U0h1uyIy6h04OIXcpTP5dNEHxLkkDwoE4fRMQKNML8/YdCURTRO/Y049MFcvi2NpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f875594fe829164183f8fc4fb52e22d7b29f29eb0955ca7b1ee4b0c67e5fb8a","last_reissued_at":"2026-07-05T08:24:01.582751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:01.582751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08939","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":"2026-07-05T08:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zhgJbpHRz0cLirQ4TZwI42USn3Nz58JeFqE6YiDC6UakqigkUwyGVn5aJf9i6L+VwcC8tE1ZuhNKWA3jT4ruAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:32:17.905882Z"},"content_sha256":"96eb23bf1bfd8bb164c3d1291078d84469445e0ca255106cea85873a5dab5d00","schema_version":"1.0","event_id":"sha256:96eb23bf1bfd8bb164c3d1291078d84469445e0ca255106cea85873a5dab5d00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L6DVLFH6QKIWIGB7R7CPWUXCFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Premise Order Matters in Reasoning with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Denny Zhou, Ryan A. Chi, Xinyun Chen, Xuezhi Wang","submitted_at":"2024-02-14T04:50:18Z","abstract_excerpt":"Large language models (LLMs) have accomplished remarkable reasoning performance in various domains. However, in the domain of reasoning tasks, we discover a frailty: LLMs are surprisingly brittle to the ordering of the premises, despite the fact that such ordering does not alter the underlying task. In particular, we observe that LLMs achieve the best performance when the premise order aligns with the context required in intermediate reasoning steps. For example, in deductive reasoning tasks, presenting the premises in the same order as the ground truth proof in the prompt (as opposed to rando"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08939","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/2402.08939/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":"2026-07-05T08:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/1bqKQWLzWQ5DU/36Bh0vi1Oz3ZgN7QWh+PcWhWgNJ4IHX8tu1krILbPNx9H27utMcdv2PBM3ZpojKIoQwSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:32:17.906521Z"},"content_sha256":"9ca54dec6e1fb99cb5a1e99dc57959fdd7ca8d2dec95e2df8a58d1d17e689ab4","schema_version":"1.0","event_id":"sha256:9ca54dec6e1fb99cb5a1e99dc57959fdd7ca8d2dec95e2df8a58d1d17e689ab4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6DVLFH6QKIWIGB7R7CPWUXCFV/bundle.json","state_url":"https://pith.science/pith/L6DVLFH6QKIWIGB7R7CPWUXCFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6DVLFH6QKIWIGB7R7CPWUXCFV/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":"2026-07-05T13:32:17Z","links":{"resolver":"https://pith.science/pith/L6DVLFH6QKIWIGB7R7CPWUXCFV","bundle":"https://pith.science/pith/L6DVLFH6QKIWIGB7R7CPWUXCFV/bundle.json","state":"https://pith.science/pith/L6DVLFH6QKIWIGB7R7CPWUXCFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6DVLFH6QKIWIGB7R7CPWUXCFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L6DVLFH6QKIWIGB7R7CPWUXCFV","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":"654701d4e58c0507d9184e948dad726d351f36869d2390268207012df903bc7d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T04:50:18Z","title_canon_sha256":"a01f4cce52ba2285d96b23396284fb31c8534d7f322ffb897956b57687ad02b5"},"schema_version":"1.0","source":{"id":"2402.08939","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08939","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08939v3","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08939","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"L6DVLFH6QKIW","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"L6DVLFH6QKIWIGB7","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"L6DVLFH6","created_at":"2026-07-05T08:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:9ca54dec6e1fb99cb5a1e99dc57959fdd7ca8d2dec95e2df8a58d1d17e689ab4","target":"graph","created_at":"2026-07-05T08:24:01Z","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/2402.08939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have accomplished remarkable reasoning performance in various domains. However, in the domain of reasoning tasks, we discover a frailty: LLMs are surprisingly brittle to the ordering of the premises, despite the fact that such ordering does not alter the underlying task. In particular, we observe that LLMs achieve the best performance when the premise order aligns with the context required in intermediate reasoning steps. For example, in deductive reasoning tasks, presenting the premises in the same order as the ground truth proof in the prompt (as opposed to rando","authors_text":"Denny Zhou, Ryan A. Chi, Xinyun Chen, Xuezhi Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T04:50:18Z","title":"Premise Order Matters in Reasoning with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08939","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":"sha256:96eb23bf1bfd8bb164c3d1291078d84469445e0ca255106cea85873a5dab5d00","target":"record","created_at":"2026-07-05T08:24:01Z","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":"654701d4e58c0507d9184e948dad726d351f36869d2390268207012df903bc7d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T04:50:18Z","title_canon_sha256":"a01f4cce52ba2285d96b23396284fb31c8534d7f322ffb897956b57687ad02b5"},"schema_version":"1.0","source":{"id":"2402.08939","kind":"arxiv","version":3}},"canonical_sha256":"5f875594fe829164183f8fc4fb52e22d7b29f29eb0955ca7b1ee4b0c67e5fb8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f875594fe829164183f8fc4fb52e22d7b29f29eb0955ca7b1ee4b0c67e5fb8a","first_computed_at":"2026-07-05T08:24:01.582751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:01.582751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/Bil8IA0J165vmTnIJ8U0h1uyIy6h04OIXcpTP5dNEHxLkkDwoE4fRMQKNML8/YdCURTRO/Y049MFcvi2NpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:01.583236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08939","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96eb23bf1bfd8bb164c3d1291078d84469445e0ca255106cea85873a5dab5d00","sha256:9ca54dec6e1fb99cb5a1e99dc57959fdd7ca8d2dec95e2df8a58d1d17e689ab4"],"state_sha256":"cce8908d80bdc9182328f7fcf0a4f2791b3d73a7fa489808722e886279baeabc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4h7JVbuLqlEEXvC8R+C2w+iSifNHQ9cLW9jdAwbfm5018Vy4O1vasQlKDm8r78bzOVqnOzkqPa6aqEMCaLJkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:32:17.909596Z","bundle_sha256":"12bfffb487067f087e9326c50a8cee0be780170a7f179709f2f0775637d29f9f"}}