{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F4JKEBXIBMINHBEATR7G7I4CZA","short_pith_number":"pith:F4JKEBXI","schema_version":"1.0","canonical_sha256":"2f12a206e80b10d384809c7e6fa382c82b8c9b63f02814d1533b58475331000b","source":{"kind":"arxiv","id":"2405.12656","version":1},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chih-Yu Liu, Hsiao-Cheng Chang, Huang-Ting Shieh, Jing-Lun Yang, Kuang-Ting Lee, Yu-Hsiang Lin, Yu-Sheng Lin","submitted_at":"2024-05-21T10:10:56Z","abstract_excerpt":"Extrapolation in Large language models (LLMs) for open-ended inquiry encounters two pivotal issues: (1) hallucination and (2) expensive training costs. These issues present challenges for LLMs in specialized domains and personalized data, requiring truthful responses and low fine-tuning costs. Existing works attempt to tackle the problem by augmenting the input of a smaller language model with information from a knowledge graph (KG). However, they have two limitations: (1) failing to extract relevant information from a large one-hop neighborhood in KG and (2) applying the same augmentation str"},"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":"2405.12656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T10:10:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc06da5c39f88b0dec5f8cee533286c4b3a2b9c781f3d895a55ff99a9b65798a","abstract_canon_sha256":"d3d04ce5b725f5feebe58ba57c3d351d75b0fd2ed1dec7e2fe4c7f40fb0bcc09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:23.683680Z","signature_b64":"GxGcHGn8CCO/OJuzEhBtGr64UR4Ov9roQ4WbJ4FT5VYE6i3hyz4x/PLetlKetq6iugF2SEcUeBYPE1uNf1zhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f12a206e80b10d384809c7e6fa382c82b8c9b63f02814d1533b58475331000b","last_reissued_at":"2026-07-05T08:21:23.683263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:23.683263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chih-Yu Liu, Hsiao-Cheng Chang, Huang-Ting Shieh, Jing-Lun Yang, Kuang-Ting Lee, Yu-Hsiang Lin, Yu-Sheng Lin","submitted_at":"2024-05-21T10:10:56Z","abstract_excerpt":"Extrapolation in Large language models (LLMs) for open-ended inquiry encounters two pivotal issues: (1) hallucination and (2) expensive training costs. These issues present challenges for LLMs in specialized domains and personalized data, requiring truthful responses and low fine-tuning costs. Existing works attempt to tackle the problem by augmenting the input of a smaller language model with information from a knowledge graph (KG). However, they have two limitations: (1) failing to extract relevant information from a large one-hop neighborhood in KG and (2) applying the same augmentation str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12656","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/2405.12656/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":"2405.12656","created_at":"2026-07-05T08:21:23.683324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12656v1","created_at":"2026-07-05T08:21:23.683324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12656","created_at":"2026-07-05T08:21:23.683324+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4JKEBXIBMIN","created_at":"2026-07-05T08:21:23.683324+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4JKEBXIBMINHBEA","created_at":"2026-07-05T08:21:23.683324+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4JKEBXI","created_at":"2026-07-05T08:21:23.683324+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/F4JKEBXIBMINHBEATR7G7I4CZA","json":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA.json","graph_json":"https://pith.science/api/pith-number/F4JKEBXIBMINHBEATR7G7I4CZA/graph.json","events_json":"https://pith.science/api/pith-number/F4JKEBXIBMINHBEATR7G7I4CZA/events.json","paper":"https://pith.science/paper/F4JKEBXI"},"agent_actions":{"view_html":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA","download_json":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA.json","view_paper":"https://pith.science/paper/F4JKEBXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12656&json=true","fetch_graph":"https://pith.science/api/pith-number/F4JKEBXIBMINHBEATR7G7I4CZA/graph.json","fetch_events":"https://pith.science/api/pith-number/F4JKEBXIBMINHBEATR7G7I4CZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA/action/storage_attestation","attest_author":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA/action/author_attestation","sign_citation":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA/action/citation_signature","submit_replication":"https://pith.science/pith/F4JKEBXIBMINHBEATR7G7I4CZA/action/replication_record"}},"created_at":"2026-07-05T08:21:23.683324+00:00","updated_at":"2026-07-05T08:21:23.683324+00:00"}