{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JMRF4NZXOFD7IIQMOHJWYWFIIJ","short_pith_number":"pith:JMRF4NZX","canonical_record":{"source":{"id":"2404.01869","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:46:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3131724c5860a036521fc0e42e276aae94e9e478b8405dc1b9ce9cbdcc57775f","abstract_canon_sha256":"eb118e0217072636cd96c6599e6c3b254330e0521dbf64c0a0c2af8d5b4aefa0"},"schema_version":"1.0"},"canonical_sha256":"4b225e37377147f4220c71d36c58a84267b7d4f16023173c77cb075afceaf482","source":{"kind":"arxiv","id":"2404.01869","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01869","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01869v2","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01869","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"pith_short_12","alias_value":"JMRF4NZXOFD7","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMRF4NZXOFD7IIQM","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMRF4NZX","created_at":"2026-07-05T08:52:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JMRF4NZXOFD7IIQMOHJWYWFIIJ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01869","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:46:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3131724c5860a036521fc0e42e276aae94e9e478b8405dc1b9ce9cbdcc57775f","abstract_canon_sha256":"eb118e0217072636cd96c6599e6c3b254330e0521dbf64c0a0c2af8d5b4aefa0"},"schema_version":"1.0"},"canonical_sha256":"4b225e37377147f4220c71d36c58a84267b7d4f16023173c77cb075afceaf482","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:31.360153Z","signature_b64":"f02+CcMMKpfxdm8bCsgslSx1H+BMGg7rDGt4S87pA5mISHsITrzZLhc0h/jBPE3/7aD6exsR+YRH6GgmgNBAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b225e37377147f4220c71d36c58a84267b7d4f16023173c77cb075afceaf482","last_reissued_at":"2026-07-05T08:52:31.359738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:31.359738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01869","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:52:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jG7SvQIvBmTlPJASWhQHCqZkAIlKjGjaNxXH532qMLlUrNNSjSeV8yHKgXv/AIgmwHjAvsgJUFyUPhWVN8YCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:40:39.011896Z"},"content_sha256":"64a99369d44981338471b9c8ded61a47ab61f3591ec26e7ab1ad01a5c7a4d420","schema_version":"1.0","event_id":"sha256:64a99369d44981338471b9c8ded61a47ab61f3591ec26e7ab1ad01a5c7a4d420"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JMRF4NZXOFD7IIQMOHJWYWFIIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Philipp Mondorf","submitted_at":"2024-04-02T11:46:31Z","abstract_excerpt":"Large language models (LLMs) have recently shown impressive performance on tasks involving reasoning, leading to a lively debate on whether these models possess reasoning capabilities similar to humans. However, despite these successes, the depth of LLMs' reasoning abilities remains uncertain. This uncertainty partly stems from the predominant focus on task performance, measured through shallow accuracy metrics, rather than a thorough investigation of the models' reasoning behavior. This paper seeks to address this gap by providing a comprehensive review of studies that go beyond task accuracy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01869","kind":"arxiv","version":2},"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/2404.01869/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":"2026-07-05T08:52:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ooTTl6s7DiXPoejXrcstOGPqQivBB6PWBZifNdneasCKS2ZZMTvORNdDM+gRogAPyZON3gYsaYPsycG5VJavCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:40:39.012385Z"},"content_sha256":"69963e838d7510024956b4edb451116647777995b192b4a12553f595c0233b77","schema_version":"1.0","event_id":"sha256:69963e838d7510024956b4edb451116647777995b192b4a12553f595c0233b77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMRF4NZXOFD7IIQMOHJWYWFIIJ/bundle.json","state_url":"https://pith.science/pith/JMRF4NZXOFD7IIQMOHJWYWFIIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMRF4NZXOFD7IIQMOHJWYWFIIJ/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":"2026-08-09T03:40:39Z","links":{"resolver":"https://pith.science/pith/JMRF4NZXOFD7IIQMOHJWYWFIIJ","bundle":"https://pith.science/pith/JMRF4NZXOFD7IIQMOHJWYWFIIJ/bundle.json","state":"https://pith.science/pith/JMRF4NZXOFD7IIQMOHJWYWFIIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMRF4NZXOFD7IIQMOHJWYWFIIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JMRF4NZXOFD7IIQMOHJWYWFIIJ","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":"eb118e0217072636cd96c6599e6c3b254330e0521dbf64c0a0c2af8d5b4aefa0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:46:31Z","title_canon_sha256":"3131724c5860a036521fc0e42e276aae94e9e478b8405dc1b9ce9cbdcc57775f"},"schema_version":"1.0","source":{"id":"2404.01869","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01869","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01869v2","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01869","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"pith_short_12","alias_value":"JMRF4NZXOFD7","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMRF4NZXOFD7IIQM","created_at":"2026-07-05T08:52:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMRF4NZX","created_at":"2026-07-05T08:52:31Z"}],"graph_snapshots":[{"event_id":"sha256:69963e838d7510024956b4edb451116647777995b192b4a12553f595c0233b77","target":"graph","created_at":"2026-07-05T08:52:31Z","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/2404.01869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently shown impressive performance on tasks involving reasoning, leading to a lively debate on whether these models possess reasoning capabilities similar to humans. However, despite these successes, the depth of LLMs' reasoning abilities remains uncertain. This uncertainty partly stems from the predominant focus on task performance, measured through shallow accuracy metrics, rather than a thorough investigation of the models' reasoning behavior. This paper seeks to address this gap by providing a comprehensive review of studies that go beyond task accuracy","authors_text":"Barbara Plank, Philipp Mondorf","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:46:31Z","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01869","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":"sha256:64a99369d44981338471b9c8ded61a47ab61f3591ec26e7ab1ad01a5c7a4d420","target":"record","created_at":"2026-07-05T08:52:31Z","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":"eb118e0217072636cd96c6599e6c3b254330e0521dbf64c0a0c2af8d5b4aefa0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:46:31Z","title_canon_sha256":"3131724c5860a036521fc0e42e276aae94e9e478b8405dc1b9ce9cbdcc57775f"},"schema_version":"1.0","source":{"id":"2404.01869","kind":"arxiv","version":2}},"canonical_sha256":"4b225e37377147f4220c71d36c58a84267b7d4f16023173c77cb075afceaf482","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b225e37377147f4220c71d36c58a84267b7d4f16023173c77cb075afceaf482","first_computed_at":"2026-07-05T08:52:31.359738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:31.359738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f02+CcMMKpfxdm8bCsgslSx1H+BMGg7rDGt4S87pA5mISHsITrzZLhc0h/jBPE3/7aD6exsR+YRH6GgmgNBAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:31.360153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01869","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64a99369d44981338471b9c8ded61a47ab61f3591ec26e7ab1ad01a5c7a4d420","sha256:69963e838d7510024956b4edb451116647777995b192b4a12553f595c0233b77"],"state_sha256":"430b02ddf7c56f2fa8233f08ee047a9fbeeac95f5dbe40829fce4b8f12599423"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jY+NNQJvYxU4aFOkfxeRWOESTHXsFPnVjvVYdALjyELWys32sW7uqMPmtD4vOjzWp7uQBKoo+bFNHjyKwG75CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:40:39.016674Z","bundle_sha256":"f6a0893849ca9a1dd02bb7623e99fc9571b3787d20e5ffdb7a7ec7649b8e14c1"}}