{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZHRUXFJGMXULGV3GWDEN4LWDW4","short_pith_number":"pith:ZHRUXFJG","canonical_record":{"source":{"id":"2608.03729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T14:25:47Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"ad2fb255a8b7875341cebef7db2876add71cc7921b385abdbc837cb595073821","abstract_canon_sha256":"642a3cffbf5bd72643554c4d8f481343531ff4d20f0970476a55ecace4172ec3"},"schema_version":"1.0"},"canonical_sha256":"c9e34b952665e8b35766b0c8de2ec3b727a3cd267f1d25fbe5aa348b02e1aace","source":{"kind":"arxiv","id":"2608.03729","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03729","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03729v1","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03729","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZHRUXFJGMXUL","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZHRUXFJGMXULGV3G","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZHRUXFJG","created_at":"2026-08-05T01:36:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZHRUXFJGMXULGV3GWDEN4LWDW4","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T14:25:47Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"ad2fb255a8b7875341cebef7db2876add71cc7921b385abdbc837cb595073821","abstract_canon_sha256":"642a3cffbf5bd72643554c4d8f481343531ff4d20f0970476a55ecace4172ec3"},"schema_version":"1.0"},"canonical_sha256":"c9e34b952665e8b35766b0c8de2ec3b727a3cd267f1d25fbe5aa348b02e1aace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:36:58.361558Z","signature_b64":"Viym4mY8ITMVeAgQiZ3aBcbCKQB0qeXZc1tVkR30irUdlyTuJAH+Kqn32Y+fie+Kjrx4588Max2C/EKFPq6+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9e34b952665e8b35766b0c8de2ec3b727a3cd267f1d25fbe5aa348b02e1aace","last_reissued_at":"2026-08-05T01:36:58.360135Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:36:58.360135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03729","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":"2026-08-05T01:36:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XF5YpPFP4ZUatn19rczGdVsv3QWZdHeVeovQREmv8BD3o4NLxm/4tg4vPzmIJnLy1z8YKjpRyGn+Nk6QId0RAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:55:01.075568Z"},"content_sha256":"0c9df36db6799359667997c7a1488c17a91a30fb83c46dd092e2c08331c24869","schema_version":"1.0","event_id":"sha256:0c9df36db6799359667997c7a1488c17a91a30fb83c46dd092e2c08331c24869"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZHRUXFJGMXULGV3GWDEN4LWDW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Simon Razniewski, Tuan-Phong Nguyen, Yujia Hu","submitted_at":"2026-08-04T14:25:47Z","abstract_excerpt":"Automated Knowledge Base Construction (AKBC) is a core NLP task, and recent work proposes generating knowledge bases directly from large language models (LLMs), treating the model itself as the knowledge source. However, LLMs natively possess no representation of entities, leading to duplicate entries as well as conflations. We propose GPTKB 2.0, a methodology for constructing disambiguated KBs directly from LLMs. GPTKB 2.0 incorporates on-the-fly disambiguation of entities, relations and classes, and is meticulously designed to satisfy both scalability and disambiguation accuracy. We analyze "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03729","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/2608.03729/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":"2026-08-05T01:36:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3X9DUIEZ9Stv+H5s9we3FKAVaIYtkVK4H6ku2dJHzzAmY/MGXI71rNkPX2e1v5P0uGaNQy8AYsUoJiCWlNkKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:55:01.076738Z"},"content_sha256":"96c9cb825c831b6953216afaa764e01cdea2e410fbbd0a51d3aecd2f1fbd49fa","schema_version":"1.0","event_id":"sha256:96c9cb825c831b6953216afaa764e01cdea2e410fbbd0a51d3aecd2f1fbd49fa"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:ZHRUXFJGMXULGV3GWDEN4LWDW4","target":"integrity","payload":{"note":"Identifier '10.1207/s15516709cog2901' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Mark Steyvers and Joshua B. Tenenbaum , title =. Cogn. Sci. , volume =. 2005 , url =. doi:10.1207/S15516709COG2901\\_3 , timestamp =","arxiv_id":"2608.03729","detector":"doi_compliance","evidence":{"doi":"10.1207/s15516709cog2901","arxiv_id":null,"ref_index":31,"raw_excerpt":"Mark Steyvers and Joshua B. Tenenbaum , title =. Cogn. Sci. , volume =. 2005 , url =. doi:10.1207/S15516709COG2901\\_3 , timestamp =","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":31,"audited_at":"2026-08-05T14:08:17.331570Z","event_type":"pith.integrity.v1","detected_doi":"10.1207/s15516709cog2901","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"2b6a7603884b801b490da993a185b0d81ae43a3da321da860a72ed299dca4841","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18079,"payload_sha256":"297e6d84a15e0f12b88aa35f9a268d9030575c8d14ae9e9da77009cd43492f08","signature_b64":"C6KtsdN+Ho51IlY+xoWnGkjf9KxEvAbNGZItBOLxYpwNwPMzka4+4TgUPHpZPW3WoQJJnHpddlhPNejo4i0aAw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T14:08:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2tAo3u4h1PK291AlbTJNMiNcCqtlMKaQh08NmB+HjTP9IMQI10pp+qQrsqH2A68rRejfmR2vUyN3ArdIDzuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:55:01.088919Z"},"content_sha256":"f50f3cdd749a63760259914fbca759d0da77012545876cfc428741620fcdfee2","schema_version":"1.0","event_id":"sha256:f50f3cdd749a63760259914fbca759d0da77012545876cfc428741620fcdfee2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHRUXFJGMXULGV3GWDEN4LWDW4/bundle.json","state_url":"https://pith.science/pith/ZHRUXFJGMXULGV3GWDEN4LWDW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHRUXFJGMXULGV3GWDEN4LWDW4/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":"2026-08-06T01:55:01Z","links":{"resolver":"https://pith.science/pith/ZHRUXFJGMXULGV3GWDEN4LWDW4","bundle":"https://pith.science/pith/ZHRUXFJGMXULGV3GWDEN4LWDW4/bundle.json","state":"https://pith.science/pith/ZHRUXFJGMXULGV3GWDEN4LWDW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHRUXFJGMXULGV3GWDEN4LWDW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZHRUXFJGMXULGV3GWDEN4LWDW4","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"642a3cffbf5bd72643554c4d8f481343531ff4d20f0970476a55ecace4172ec3","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T14:25:47Z","title_canon_sha256":"ad2fb255a8b7875341cebef7db2876add71cc7921b385abdbc837cb595073821"},"schema_version":"1.0","source":{"id":"2608.03729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03729","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03729v1","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03729","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZHRUXFJGMXUL","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZHRUXFJGMXULGV3G","created_at":"2026-08-05T01:36:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZHRUXFJG","created_at":"2026-08-05T01:36:58Z"}],"graph_snapshots":[{"event_id":"sha256:96c9cb825c831b6953216afaa764e01cdea2e410fbbd0a51d3aecd2f1fbd49fa","target":"graph","created_at":"2026-08-05T01:36:58Z","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/2608.03729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated Knowledge Base Construction (AKBC) is a core NLP task, and recent work proposes generating knowledge bases directly from large language models (LLMs), treating the model itself as the knowledge source. However, LLMs natively possess no representation of entities, leading to duplicate entries as well as conflations. We propose GPTKB 2.0, a methodology for constructing disambiguated KBs directly from LLMs. GPTKB 2.0 incorporates on-the-fly disambiguation of entities, relations and classes, and is meticulously designed to satisfy both scalability and disambiguation accuracy. We analyze ","authors_text":"Simon Razniewski, Tuan-Phong Nguyen, Yujia Hu","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T14:25:47Z","title":"GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03729","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":"sha256:0c9df36db6799359667997c7a1488c17a91a30fb83c46dd092e2c08331c24869","target":"record","created_at":"2026-08-05T01:36:58Z","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":"642a3cffbf5bd72643554c4d8f481343531ff4d20f0970476a55ecace4172ec3","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T14:25:47Z","title_canon_sha256":"ad2fb255a8b7875341cebef7db2876add71cc7921b385abdbc837cb595073821"},"schema_version":"1.0","source":{"id":"2608.03729","kind":"arxiv","version":1}},"canonical_sha256":"c9e34b952665e8b35766b0c8de2ec3b727a3cd267f1d25fbe5aa348b02e1aace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9e34b952665e8b35766b0c8de2ec3b727a3cd267f1d25fbe5aa348b02e1aace","first_computed_at":"2026-08-05T01:36:58.360135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:36:58.360135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Viym4mY8ITMVeAgQiZ3aBcbCKQB0qeXZc1tVkR30irUdlyTuJAH+Kqn32Y+fie+Kjrx4588Max2C/EKFPq6+Cw==","signature_status":"signed_v1","signed_at":"2026-08-05T01:36:58.361558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c9df36db6799359667997c7a1488c17a91a30fb83c46dd092e2c08331c24869","sha256:96c9cb825c831b6953216afaa764e01cdea2e410fbbd0a51d3aecd2f1fbd49fa","sha256:f50f3cdd749a63760259914fbca759d0da77012545876cfc428741620fcdfee2"],"state_sha256":"7945326aee3b88d16e47f8f143772bb455df0a5adf72e6ccef4f92f54c56656c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DrJXMM8cmbXOKFQ7lACYv+rPnTpGHmA28ckpbMag7jgVnPJC/8B3MenhTABFjv3ot0RouHuuPTGu743mctPmAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:55:01.092564Z","bundle_sha256":"5521b6a0ab55961b93a8833fcb59a97c458ef06ade91d994cc5d5862e8814820"}}