{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PX5Y3QG3YWT7PPBCDC66LJW4QM","short_pith_number":"pith:PX5Y3QG3","schema_version":"1.0","canonical_sha256":"7dfb8dc0dbc5a7f7bc2218bde5a6dc83282621e8472b60c4ac1fb8e8bf8da913","source":{"kind":"arxiv","id":"2608.07023","version":1},"attestation_state":"computed","paper":{"title":"An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Emma Jouffroy, Marc Palyart, Warren Jouanneau","submitted_at":"2026-08-07T09:32:25Z","abstract_excerpt":"Organizing thousands of unstandardized, multilingual expertise declarations is a persistent challenge for Human Resources (HR) platforms, directly impacting downstream tasks like accurate talent matching. To address this, we propose a hybrid knowledge graph generation pipeline that grounds a Large Language Model (LLM) in the Wikidata multilingual Knowledge Graph (KG) while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata. Unlike rigid top-down methods or fragmented bottom-up approaches, our system anchors recognized concepts to stable Knowled"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.07023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T09:32:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dd502b6c9b621243c0dfa0934b403ffd770b661888ad76081ee0d34e2c5c8140","abstract_canon_sha256":"1b0328263bea361b195d1423913391b3c4ea207dfd76eaa323c86d38a9191d5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:53.810891Z","signature_b64":"R8UmmczxEyrA0Ed65iNnIcpy3qub645CH8O1xeOlfSBw4bWgsbDbIabhDZ/nYv5teQ7/ocoWTs4Hof5R/ReqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dfb8dc0dbc5a7f7bc2218bde5a6dc83282621e8472b60c4ac1fb8e8bf8da913","last_reissued_at":"2026-08-10T01:12:53.807934Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:53.807934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Emma Jouffroy, Marc Palyart, Warren Jouanneau","submitted_at":"2026-08-07T09:32:25Z","abstract_excerpt":"Organizing thousands of unstandardized, multilingual expertise declarations is a persistent challenge for Human Resources (HR) platforms, directly impacting downstream tasks like accurate talent matching. To address this, we propose a hybrid knowledge graph generation pipeline that grounds a Large Language Model (LLM) in the Wikidata multilingual Knowledge Graph (KG) while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata. Unlike rigid top-down methods or fragmented bottom-up approaches, our system anchors recognized concepts to stable Knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07023","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/2608.07023/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.07023","created_at":"2026-08-10T01:12:53.809269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07023v1","created_at":"2026-08-10T01:12:53.809269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07023","created_at":"2026-08-10T01:12:53.809269+00:00"},{"alias_kind":"pith_short_12","alias_value":"PX5Y3QG3YWT7","created_at":"2026-08-10T01:12:53.809269+00:00"},{"alias_kind":"pith_short_16","alias_value":"PX5Y3QG3YWT7PPBC","created_at":"2026-08-10T01:12:53.809269+00:00"},{"alias_kind":"pith_short_8","alias_value":"PX5Y3QG3","created_at":"2026-08-10T01:12:53.809269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM","json":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM.json","graph_json":"https://pith.science/api/pith-number/PX5Y3QG3YWT7PPBCDC66LJW4QM/graph.json","events_json":"https://pith.science/api/pith-number/PX5Y3QG3YWT7PPBCDC66LJW4QM/events.json","paper":"https://pith.science/paper/PX5Y3QG3"},"agent_actions":{"view_html":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM","download_json":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM.json","view_paper":"https://pith.science/paper/PX5Y3QG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07023&json=true","fetch_graph":"https://pith.science/api/pith-number/PX5Y3QG3YWT7PPBCDC66LJW4QM/graph.json","fetch_events":"https://pith.science/api/pith-number/PX5Y3QG3YWT7PPBCDC66LJW4QM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM/action/storage_attestation","attest_author":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM/action/author_attestation","sign_citation":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM/action/citation_signature","submit_replication":"https://pith.science/pith/PX5Y3QG3YWT7PPBCDC66LJW4QM/action/replication_record"}},"created_at":"2026-08-10T01:12:53.809269+00:00","updated_at":"2026-08-10T01:12:53.809269+00:00"}