{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NL2GIUNQHNRWWTXCGHNDOO4IPP","short_pith_number":"pith:NL2GIUNQ","schema_version":"1.0","canonical_sha256":"6af46451b03b636b4ee231da373b887bfd35d4091d048c138cf8f6766cfb3294","source":{"kind":"arxiv","id":"2508.04474","version":1},"attestation_state":"computed","paper":{"title":"TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guanjie Cheng, Haode Li, Xinkui Zhao, Yifan Zhang, Yueshen Xu","submitted_at":"2025-08-06T14:25:05Z","abstract_excerpt":"Recent advances in large language models (LLMs) have unlocked powerful reasoning and decision-making capabilities. However, their inherent dependence on static parametric memory fundamentally limits their adaptability, factual accuracy, and interpretability in knowledge-intensive scenarios. Knowledge graphs (KGs), as structured repositories of explicit relational knowledge, offer a promising approach for augmenting LLMs with external, interpretable memory. Nevertheless, most existing methods that combine LLMs with KGs treat reasoning and knowledge updating as separate processes, resulting in s"},"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":"2508.04474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T14:25:05Z","cross_cats_sorted":[],"title_canon_sha256":"c6d145be53b5ee1ac8aa11263814752d48d6145f480f42ba500c4460c3c4c5f6","abstract_canon_sha256":"cf0d3164330424508abd20ef92efed75fc886c1ba5b6c4369aca1cba6666547e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:37.483943Z","signature_b64":"B0Bv4Yj9KNTg+2BnfFFN4yeVypjCHY13gehLksvlrnd+4u4/pgNcr7B//2RHdfuaSRb3zPF4FyzJNsJQSHRPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6af46451b03b636b4ee231da373b887bfd35d4091d048c138cf8f6766cfb3294","last_reissued_at":"2026-07-05T11:49:37.483403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:37.483403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guanjie Cheng, Haode Li, Xinkui Zhao, Yifan Zhang, Yueshen Xu","submitted_at":"2025-08-06T14:25:05Z","abstract_excerpt":"Recent advances in large language models (LLMs) have unlocked powerful reasoning and decision-making capabilities. However, their inherent dependence on static parametric memory fundamentally limits their adaptability, factual accuracy, and interpretability in knowledge-intensive scenarios. Knowledge graphs (KGs), as structured repositories of explicit relational knowledge, offer a promising approach for augmenting LLMs with external, interpretable memory. Nevertheless, most existing methods that combine LLMs with KGs treat reasoning and knowledge updating as separate processes, resulting in s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04474","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/2508.04474/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":"2508.04474","created_at":"2026-07-05T11:49:37.483470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04474v1","created_at":"2026-07-05T11:49:37.483470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04474","created_at":"2026-07-05T11:49:37.483470+00:00"},{"alias_kind":"pith_short_12","alias_value":"NL2GIUNQHNRW","created_at":"2026-07-05T11:49:37.483470+00:00"},{"alias_kind":"pith_short_16","alias_value":"NL2GIUNQHNRWWTXC","created_at":"2026-07-05T11:49:37.483470+00:00"},{"alias_kind":"pith_short_8","alias_value":"NL2GIUNQ","created_at":"2026-07-05T11:49:37.483470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16402","citing_title":"GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10488","citing_title":"DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP","json":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP.json","graph_json":"https://pith.science/api/pith-number/NL2GIUNQHNRWWTXCGHNDOO4IPP/graph.json","events_json":"https://pith.science/api/pith-number/NL2GIUNQHNRWWTXCGHNDOO4IPP/events.json","paper":"https://pith.science/paper/NL2GIUNQ"},"agent_actions":{"view_html":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP","download_json":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP.json","view_paper":"https://pith.science/paper/NL2GIUNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04474&json=true","fetch_graph":"https://pith.science/api/pith-number/NL2GIUNQHNRWWTXCGHNDOO4IPP/graph.json","fetch_events":"https://pith.science/api/pith-number/NL2GIUNQHNRWWTXCGHNDOO4IPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP/action/storage_attestation","attest_author":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP/action/author_attestation","sign_citation":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP/action/citation_signature","submit_replication":"https://pith.science/pith/NL2GIUNQHNRWWTXCGHNDOO4IPP/action/replication_record"}},"created_at":"2026-07-05T11:49:37.483470+00:00","updated_at":"2026-07-05T11:49:37.483470+00:00"}