{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VPN4IFGHZYOTARTBH3AVSEYHM2","short_pith_number":"pith:VPN4IFGH","canonical_record":{"source":{"id":"2310.09430","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:29:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4aa3c998834d0abdf41fff867cd5f61de8654c5dbd973f5d57fe9e41a2213a90","abstract_canon_sha256":"7ad5a3b63bc54371b291f236215ba6b4daf0e296f180b4300f9b097f539b64b9"},"schema_version":"1.0"},"canonical_sha256":"abdbc414c7ce1d3046613ec159130766b31601aba198c4b26a87cd898f0744e7","source":{"kind":"arxiv","id":"2310.09430","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09430","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09430v5","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09430","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"VPN4IFGHZYOT","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"VPN4IFGHZYOTARTB","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"VPN4IFGH","created_at":"2026-07-05T10:02:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VPN4IFGHZYOTARTBH3AVSEYHM2","target":"record","payload":{"canonical_record":{"source":{"id":"2310.09430","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:29:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4aa3c998834d0abdf41fff867cd5f61de8654c5dbd973f5d57fe9e41a2213a90","abstract_canon_sha256":"7ad5a3b63bc54371b291f236215ba6b4daf0e296f180b4300f9b097f539b64b9"},"schema_version":"1.0"},"canonical_sha256":"abdbc414c7ce1d3046613ec159130766b31601aba198c4b26a87cd898f0744e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:00.865572Z","signature_b64":"odMhyaD+EVbga2tgAsJFjEwemgTFpdFGXgeP08el/97anPtS509hVaAxWRzcx1KZf8PpTSS5C8Fc45n5JVHcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abdbc414c7ce1d3046613ec159130766b31601aba198c4b26a87cd898f0744e7","last_reissued_at":"2026-07-05T10:02:00.865072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:00.865072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.09430","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBxxaWGVK9I1Yy00rx44hGWZAK1GSIzkklzCqds6MptyAWzuwPRzqPOxf8OH0Og7uw/1Jjd79nUNgB/5tQ4mCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T01:07:49.579549Z"},"content_sha256":"f78975125f92f9ac3af5151ba7d2607dc064cdd8eda790f1f8be62c7c4141bd2","schema_version":"1.0","event_id":"sha256:f78975125f92f9ac3af5151ba7d2607dc064cdd8eda790f1f8be62c7c4141bd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VPN4IFGHZYOTARTBH3AVSEYHM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Yuxuan Peng, Gael Gendron, Jiamou Liu, Michael Witbrock, Neset Tan, Qiming Bao, Wanjun Zhong, Yang Chen","submitted_at":"2023-10-13T22:29:15Z","abstract_excerpt":"Large language models (LLMs), such as LLaMA, Alpaca, Vicuna, GPT-3.5 and GPT-4, have advanced the performance of AI systems on various natural language processing tasks to human-like levels. However, their generalisation and robustness when performing logical reasoning has not been sufficiently assessed. To comprehensively evaluate this ability, we develop three new logical reasoning datasets named \"ReClor-plus\", \"LogiQA-plus\" and \"LogiQAv2-plus\" that extend standard logical reasoning datasets to evaluate the robustness of the LLM's reasoning. For each, we create three subsets: the first with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09430","kind":"arxiv","version":5},"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/2310.09430/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":"2026-07-05T10:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVAvZMZ0hHwh4hHc9Blvp+uprcc/slO1FPGH+GSJQsawkggYumJDA2JCEa0J5O7Bu/KEkacXAELAECOASpXnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T01:07:49.580044Z"},"content_sha256":"de0108a88ff531747f6759f8f2dee3ad249464fa938b8eb4e2ee702584405825","schema_version":"1.0","event_id":"sha256:de0108a88ff531747f6759f8f2dee3ad249464fa938b8eb4e2ee702584405825"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPN4IFGHZYOTARTBH3AVSEYHM2/bundle.json","state_url":"https://pith.science/pith/VPN4IFGHZYOTARTBH3AVSEYHM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPN4IFGHZYOTARTBH3AVSEYHM2/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":"2026-08-24T01:07:49Z","links":{"resolver":"https://pith.science/pith/VPN4IFGHZYOTARTBH3AVSEYHM2","bundle":"https://pith.science/pith/VPN4IFGHZYOTARTBH3AVSEYHM2/bundle.json","state":"https://pith.science/pith/VPN4IFGHZYOTARTBH3AVSEYHM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPN4IFGHZYOTARTBH3AVSEYHM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VPN4IFGHZYOTARTBH3AVSEYHM2","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":"7ad5a3b63bc54371b291f236215ba6b4daf0e296f180b4300f9b097f539b64b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:29:15Z","title_canon_sha256":"4aa3c998834d0abdf41fff867cd5f61de8654c5dbd973f5d57fe9e41a2213a90"},"schema_version":"1.0","source":{"id":"2310.09430","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09430","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09430v5","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09430","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"VPN4IFGHZYOT","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"VPN4IFGHZYOTARTB","created_at":"2026-07-05T10:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"VPN4IFGH","created_at":"2026-07-05T10:02:00Z"}],"graph_snapshots":[{"event_id":"sha256:de0108a88ff531747f6759f8f2dee3ad249464fa938b8eb4e2ee702584405825","target":"graph","created_at":"2026-07-05T10:02:00Z","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/2310.09430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs), such as LLaMA, Alpaca, Vicuna, GPT-3.5 and GPT-4, have advanced the performance of AI systems on various natural language processing tasks to human-like levels. However, their generalisation and robustness when performing logical reasoning has not been sufficiently assessed. To comprehensively evaluate this ability, we develop three new logical reasoning datasets named \"ReClor-plus\", \"LogiQA-plus\" and \"LogiQAv2-plus\" that extend standard logical reasoning datasets to evaluate the robustness of the LLM's reasoning. For each, we create three subsets: the first with ","authors_text":"Alex Yuxuan Peng, Gael Gendron, Jiamou Liu, Michael Witbrock, Neset Tan, Qiming Bao, Wanjun Zhong, Yang Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:29:15Z","title":"Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09430","kind":"arxiv","version":5},"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:f78975125f92f9ac3af5151ba7d2607dc064cdd8eda790f1f8be62c7c4141bd2","target":"record","created_at":"2026-07-05T10:02:00Z","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":"7ad5a3b63bc54371b291f236215ba6b4daf0e296f180b4300f9b097f539b64b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:29:15Z","title_canon_sha256":"4aa3c998834d0abdf41fff867cd5f61de8654c5dbd973f5d57fe9e41a2213a90"},"schema_version":"1.0","source":{"id":"2310.09430","kind":"arxiv","version":5}},"canonical_sha256":"abdbc414c7ce1d3046613ec159130766b31601aba198c4b26a87cd898f0744e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abdbc414c7ce1d3046613ec159130766b31601aba198c4b26a87cd898f0744e7","first_computed_at":"2026-07-05T10:02:00.865072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:00.865072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"odMhyaD+EVbga2tgAsJFjEwemgTFpdFGXgeP08el/97anPtS509hVaAxWRzcx1KZf8PpTSS5C8Fc45n5JVHcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:00.865572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09430","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f78975125f92f9ac3af5151ba7d2607dc064cdd8eda790f1f8be62c7c4141bd2","sha256:de0108a88ff531747f6759f8f2dee3ad249464fa938b8eb4e2ee702584405825"],"state_sha256":"e7a41b04a39e91e1b5d1a26ad95235836fb54dda0a22a8d0768db5219ba7896b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lBfYJ+yHCzPq02lN3cueb2+55t0BkQrlxaSci2NBgOzhkdoLkhEAl2uv2AwuabtGIVyojdCWqT3/dsyYz1YJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T01:07:49.585147Z","bundle_sha256":"770fdc7cac91efb596c737e10d29ac01f669d606c8ef540cc9476a8ef3979e2f"}}