{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GK6P2W4XCM5UHLKYH2LFQ3DLEM","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":"36a6c3e4adc943808aeec2e9851fe23b224fe80a12c173796d872f18538dcffe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:22:53Z","title_canon_sha256":"b00de5e89a550c0dd27f404c97ef091774b3c0a47b4464f66fdc6e1f73ac8b13"},"schema_version":"1.0","source":{"id":"2406.11050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11050","created_at":"2026-07-05T09:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11050v2","created_at":"2026-07-05T09:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11050","created_at":"2026-07-05T09:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"GK6P2W4XCM5U","created_at":"2026-07-05T09:15:33Z"},{"alias_kind":"pith_short_16","alias_value":"GK6P2W4XCM5UHLKY","created_at":"2026-07-05T09:15:33Z"},{"alias_kind":"pith_short_8","alias_value":"GK6P2W4X","created_at":"2026-07-05T09:15:33Z"}],"graph_snapshots":[{"event_id":"sha256:775d7603c00f220b11093d18b6f5c56fd45d5148961688580ad60467fc58b464","target":"graph","created_at":"2026-07-05T09:15:33Z","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/2406.11050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study introduces a hypothesis-testing framework to assess whether large language models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We go beyond evaluating LLMs on accuracy; rather, we aim to investigate their token bias in solving logical reasoning tasks. Specifically, we develop carefully controlled synthetic datasets, featuring conjunction fallacy and syllogistic problems. Our framework outlines a list of hypotheses where token biases are readily identifiable, with all null hypotheses assuming genuine reasoning capabilities of LLMs. The findings in thi","authors_text":"Bowen Jiang, Camillo J. Taylor, Dan Roth, Tanwi Mallick, Weijie J. Su, Xiaomeng Wang, Yangxinyu Xie, Zhuoqun Hao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:22:53Z","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11050","kind":"arxiv","version":2},"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:b4981ad5605ed11eff704cf8c77e5b5efe7129dcc9bc58ea66146113d58e05d7","target":"record","created_at":"2026-07-05T09:15:33Z","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":"36a6c3e4adc943808aeec2e9851fe23b224fe80a12c173796d872f18538dcffe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:22:53Z","title_canon_sha256":"b00de5e89a550c0dd27f404c97ef091774b3c0a47b4464f66fdc6e1f73ac8b13"},"schema_version":"1.0","source":{"id":"2406.11050","kind":"arxiv","version":2}},"canonical_sha256":"32bcfd5b97133b43ad583e96586c6b233933a9e829c6b117cd0bcfd54668bf70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32bcfd5b97133b43ad583e96586c6b233933a9e829c6b117cd0bcfd54668bf70","first_computed_at":"2026-07-05T09:15:33.698862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:33.698862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LOa10peN5UplwpMnQSotZr9bX7Ljkr2O7DDCKCGTcSz0zBnzVtq7VMTFaYO6VrwvKuOTrfGPbJHetaji/w7kAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:33.699348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4981ad5605ed11eff704cf8c77e5b5efe7129dcc9bc58ea66146113d58e05d7","sha256:775d7603c00f220b11093d18b6f5c56fd45d5148961688580ad60467fc58b464"],"state_sha256":"fa96c85418a0a4f5ac2dab64075d780c078df71a35bd802b62c8b288ac9909e0"}