{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:36KCCMXIXFLTXXEEA3CBZCJIUF","short_pith_number":"pith:36KCCMXI","canonical_record":{"source":{"id":"2412.08317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:53:26Z","cross_cats_sorted":[],"title_canon_sha256":"14457f56c10b9f5c8324ec6a84f651f0c1377d8d0eefbb6fe23ab01d1fa20a4d","abstract_canon_sha256":"0ab7204790193a787178d7556e058cf933433c7eef8c2b25083ea44e564235a0"},"schema_version":"1.0"},"canonical_sha256":"df942132e8b9573bdc8406c41c8928a1532caf5e193250d9ff328ab1b0480fdc","source":{"kind":"arxiv","id":"2412.08317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08317","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08317v1","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08317","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"pith_short_12","alias_value":"36KCCMXIXFLT","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"pith_short_16","alias_value":"36KCCMXIXFLTXXEE","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"pith_short_8","alias_value":"36KCCMXI","created_at":"2026-07-05T09:47:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:36KCCMXIXFLTXXEEA3CBZCJIUF","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:53:26Z","cross_cats_sorted":[],"title_canon_sha256":"14457f56c10b9f5c8324ec6a84f651f0c1377d8d0eefbb6fe23ab01d1fa20a4d","abstract_canon_sha256":"0ab7204790193a787178d7556e058cf933433c7eef8c2b25083ea44e564235a0"},"schema_version":"1.0"},"canonical_sha256":"df942132e8b9573bdc8406c41c8928a1532caf5e193250d9ff328ab1b0480fdc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:48.154615Z","signature_b64":"uCaX1UMKTXnzwegj4CA/C6qOd42AMPRVsqBGyFL5U3nIjB687vv+qsOnFyoWHEVfgwyKAqU8MeYDRZq1FbvTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df942132e8b9573bdc8406c41c8928a1532caf5e193250d9ff328ab1b0480fdc","last_reissued_at":"2026-07-05T09:47:48.154247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:48.154247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08317","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:47:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1jFoal8L6nQzVT6COlPwuHQTHRoraeiWzWUQoT/2aImZJy9OaXn/6JwmtucCK/xKLy7ix8pYpRxurn3yteECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:46:51.523911Z"},"content_sha256":"29ebed752592c9b80554b13166a7aabe20b0977012b325630ca6c3a8eabc6bab","schema_version":"1.0","event_id":"sha256:29ebed752592c9b80554b13166a7aabe20b0977012b325630ca6c3a8eabc6bab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:36KCCMXIXFLTXXEEA3CBZCJIUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haotong Zhang","submitted_at":"2024-12-11T11:53:26Z","abstract_excerpt":"We carry out a series of experiments to test large language models' multi-hop reasoning ability from three aspects: selecting and combining external knowledge, dealing with non-sequential reasoning tasks and generalising to data samples with larger numbers of hops. We test the GPT-3.5 model on four reasoning benchmarks with Chain-of-Thought prompting (and its variations). Our results reveal that despite the amazing performance achieved by large language models on various reasoning tasks, models still suffer from severe drawbacks which shows a large gap with humans."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08317","kind":"arxiv","version":1},"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/2412.08317/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":"2026-07-05T09:47:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+9cmR/MK/nDVlB3warcMvBWLY7F1LvKUt5DrcEm1xfQuVz8hYRz9fomWCMLqnThlCYVnQvJ1U+WnzLbhCG3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:46:51.524315Z"},"content_sha256":"cfd09caa43604c7be9585ac1e7e41fd6ba5684add230a74212507ab77d9cf35c","schema_version":"1.0","event_id":"sha256:cfd09caa43604c7be9585ac1e7e41fd6ba5684add230a74212507ab77d9cf35c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36KCCMXIXFLTXXEEA3CBZCJIUF/bundle.json","state_url":"https://pith.science/pith/36KCCMXIXFLTXXEEA3CBZCJIUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36KCCMXIXFLTXXEEA3CBZCJIUF/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":"2026-08-12T23:46:51Z","links":{"resolver":"https://pith.science/pith/36KCCMXIXFLTXXEEA3CBZCJIUF","bundle":"https://pith.science/pith/36KCCMXIXFLTXXEEA3CBZCJIUF/bundle.json","state":"https://pith.science/pith/36KCCMXIXFLTXXEEA3CBZCJIUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36KCCMXIXFLTXXEEA3CBZCJIUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:36KCCMXIXFLTXXEEA3CBZCJIUF","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":"0ab7204790193a787178d7556e058cf933433c7eef8c2b25083ea44e564235a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:53:26Z","title_canon_sha256":"14457f56c10b9f5c8324ec6a84f651f0c1377d8d0eefbb6fe23ab01d1fa20a4d"},"schema_version":"1.0","source":{"id":"2412.08317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08317","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08317v1","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08317","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"pith_short_12","alias_value":"36KCCMXIXFLT","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"pith_short_16","alias_value":"36KCCMXIXFLTXXEE","created_at":"2026-07-05T09:47:48Z"},{"alias_kind":"pith_short_8","alias_value":"36KCCMXI","created_at":"2026-07-05T09:47:48Z"}],"graph_snapshots":[{"event_id":"sha256:cfd09caa43604c7be9585ac1e7e41fd6ba5684add230a74212507ab77d9cf35c","target":"graph","created_at":"2026-07-05T09:47:48Z","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/2412.08317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We carry out a series of experiments to test large language models' multi-hop reasoning ability from three aspects: selecting and combining external knowledge, dealing with non-sequential reasoning tasks and generalising to data samples with larger numbers of hops. We test the GPT-3.5 model on four reasoning benchmarks with Chain-of-Thought prompting (and its variations). Our results reveal that despite the amazing performance achieved by large language models on various reasoning tasks, models still suffer from severe drawbacks which shows a large gap with humans.","authors_text":"Haotong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:53:26Z","title":"Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08317","kind":"arxiv","version":1},"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":"sha256:29ebed752592c9b80554b13166a7aabe20b0977012b325630ca6c3a8eabc6bab","target":"record","created_at":"2026-07-05T09:47:48Z","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":"0ab7204790193a787178d7556e058cf933433c7eef8c2b25083ea44e564235a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:53:26Z","title_canon_sha256":"14457f56c10b9f5c8324ec6a84f651f0c1377d8d0eefbb6fe23ab01d1fa20a4d"},"schema_version":"1.0","source":{"id":"2412.08317","kind":"arxiv","version":1}},"canonical_sha256":"df942132e8b9573bdc8406c41c8928a1532caf5e193250d9ff328ab1b0480fdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df942132e8b9573bdc8406c41c8928a1532caf5e193250d9ff328ab1b0480fdc","first_computed_at":"2026-07-05T09:47:48.154247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:48.154247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uCaX1UMKTXnzwegj4CA/C6qOd42AMPRVsqBGyFL5U3nIjB687vv+qsOnFyoWHEVfgwyKAqU8MeYDRZq1FbvTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:48.154615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29ebed752592c9b80554b13166a7aabe20b0977012b325630ca6c3a8eabc6bab","sha256:cfd09caa43604c7be9585ac1e7e41fd6ba5684add230a74212507ab77d9cf35c"],"state_sha256":"07357f7447651b57740c20a6f06c295699d35bc048b82118bdc97d44132fd37f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGtLrs5v9/bZRExELWzXMKfkxxReTciE6KLQsplYA6MbvpD6O1Hf32P/cgRyzDAtyMfI/6poZvHMNY/2jWEbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:46:51.536911Z","bundle_sha256":"83daca19ac808bef348121919b42b7a728ea22c8c298d87bcc535d9598f6d269"}}