{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VTJJUDDFOHKZ35F2GKJ3CJKDAE","short_pith_number":"pith:VTJJUDDF","schema_version":"1.0","canonical_sha256":"acd29a0c6571d59df4ba3293b1254301239e6c5f1d729193826e798402cd2405","source":{"kind":"arxiv","id":"2407.18752","version":3},"attestation_state":"computed","paper":{"title":"Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Michael F\\\"arber, Yuni Susanti","submitted_at":"2024-07-26T14:07:00Z","abstract_excerpt":"Causal discovery aims to estimate causal structures among variables based on observational data. Large Language Models (LLMs) offer a fresh perspective to tackle the causal discovery problem by reasoning on the metadata associated with variables rather than their actual data values, an approach referred to as knowledge-based causal discovery. In this paper, we investigate the capabilities of Small Language Models (SLMs, defined as LLMs with fewer than 1 billion parameters) with prompt-based learning for knowledge-based causal discovery. Specifically, we present KG Structure as Prompt, a novel "},"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":"2407.18752","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T14:07:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42eb5f682eca5527f7e51e409bc06f59f1f7696586d0978768b19bc1ef2e1764","abstract_canon_sha256":"528f0e08f37f5082d6c33872df4544081b0b4f99447a73fb7bc813f90c8abbbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:14.563264Z","signature_b64":"3M+fdMO1//aNPO/1gVKQC45E4NcbIWAMXeukEI0nUymMcIESsPwm/LD3lMgXLeoCbmlkUoB7T3JaQCrPckh5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acd29a0c6571d59df4ba3293b1254301239e6c5f1d729193826e798402cd2405","last_reissued_at":"2026-07-05T08:50:14.562889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:14.562889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Michael F\\\"arber, Yuni Susanti","submitted_at":"2024-07-26T14:07:00Z","abstract_excerpt":"Causal discovery aims to estimate causal structures among variables based on observational data. Large Language Models (LLMs) offer a fresh perspective to tackle the causal discovery problem by reasoning on the metadata associated with variables rather than their actual data values, an approach referred to as knowledge-based causal discovery. In this paper, we investigate the capabilities of Small Language Models (SLMs, defined as LLMs with fewer than 1 billion parameters) with prompt-based learning for knowledge-based causal discovery. Specifically, we present KG Structure as Prompt, a novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18752","kind":"arxiv","version":3},"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/2407.18752/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":"2407.18752","created_at":"2026-07-05T08:50:14.562943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18752v3","created_at":"2026-07-05T08:50:14.562943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18752","created_at":"2026-07-05T08:50:14.562943+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTJJUDDFOHKZ","created_at":"2026-07-05T08:50:14.562943+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTJJUDDFOHKZ35F2","created_at":"2026-07-05T08:50:14.562943+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTJJUDDF","created_at":"2026-07-05T08:50:14.562943+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/VTJJUDDFOHKZ35F2GKJ3CJKDAE","json":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE.json","graph_json":"https://pith.science/api/pith-number/VTJJUDDFOHKZ35F2GKJ3CJKDAE/graph.json","events_json":"https://pith.science/api/pith-number/VTJJUDDFOHKZ35F2GKJ3CJKDAE/events.json","paper":"https://pith.science/paper/VTJJUDDF"},"agent_actions":{"view_html":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE","download_json":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE.json","view_paper":"https://pith.science/paper/VTJJUDDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18752&json=true","fetch_graph":"https://pith.science/api/pith-number/VTJJUDDFOHKZ35F2GKJ3CJKDAE/graph.json","fetch_events":"https://pith.science/api/pith-number/VTJJUDDFOHKZ35F2GKJ3CJKDAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE/action/storage_attestation","attest_author":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE/action/author_attestation","sign_citation":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE/action/citation_signature","submit_replication":"https://pith.science/pith/VTJJUDDFOHKZ35F2GKJ3CJKDAE/action/replication_record"}},"created_at":"2026-07-05T08:50:14.562943+00:00","updated_at":"2026-07-05T08:50:14.562943+00:00"}