{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GAIPKFQ4IENLYXP6BTZXSQYAXK","short_pith_number":"pith:GAIPKFQ4","schema_version":"1.0","canonical_sha256":"3010f5161c411abc5dfe0cf3794300ba8985f12e54cbaa4dd711a404975b65db","source":{"kind":"arxiv","id":"2509.06531","version":1},"attestation_state":"computed","paper":{"title":"SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chun Yang, Jiafan Li, Jiaqi Zhu, Jingqi Zhang, Mengxue Yang, Ying Li, Yuyang Li","submitted_at":"2025-09-08T10:36:49Z","abstract_excerpt":"Link prediction in knowledge graphs requires integrating structural information and semantic context to infer missing entities. While large language models offer strong generative reasoning capabilities, their limited exploitation of structural signals often results in structural sparsity and semantic ambiguity, especially under incomplete or zero-shot settings. To address these challenges, we propose SLiNT (Structure-aware Language model with Injection and coNtrastive Training), a modular framework that injects knowledge-graph-derived structural context into a frozen LLM backbone with lightwe"},"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":"2509.06531","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T10:36:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50fbcced6e2563340d7620cae1686ea1c5213b403a69d38ed4997d36c73d0e5f","abstract_canon_sha256":"12f2708dd4ca8dcc99046af02d5ceb7ca053d4697e427568bf6ac7e46f16435c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:37.748417Z","signature_b64":"SVnJP77LtFEYN3U8RSB3ZQJaHB/FE9msio+uE1NPQ1HQiPYZLzkVsSBa1YoGii2jQfI8a1FUIM3XCrR3syrGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3010f5161c411abc5dfe0cf3794300ba8985f12e54cbaa4dd711a404975b65db","last_reissued_at":"2026-07-05T12:06:37.747928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:37.747928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chun Yang, Jiafan Li, Jiaqi Zhu, Jingqi Zhang, Mengxue Yang, Ying Li, Yuyang Li","submitted_at":"2025-09-08T10:36:49Z","abstract_excerpt":"Link prediction in knowledge graphs requires integrating structural information and semantic context to infer missing entities. While large language models offer strong generative reasoning capabilities, their limited exploitation of structural signals often results in structural sparsity and semantic ambiguity, especially under incomplete or zero-shot settings. To address these challenges, we propose SLiNT (Structure-aware Language model with Injection and coNtrastive Training), a modular framework that injects knowledge-graph-derived structural context into a frozen LLM backbone with lightwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06531","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/2509.06531/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":"2509.06531","created_at":"2026-07-05T12:06:37.747984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06531v1","created_at":"2026-07-05T12:06:37.747984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06531","created_at":"2026-07-05T12:06:37.747984+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAIPKFQ4IENL","created_at":"2026-07-05T12:06:37.747984+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAIPKFQ4IENLYXP6","created_at":"2026-07-05T12:06:37.747984+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAIPKFQ4","created_at":"2026-07-05T12:06:37.747984+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/GAIPKFQ4IENLYXP6BTZXSQYAXK","json":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK.json","graph_json":"https://pith.science/api/pith-number/GAIPKFQ4IENLYXP6BTZXSQYAXK/graph.json","events_json":"https://pith.science/api/pith-number/GAIPKFQ4IENLYXP6BTZXSQYAXK/events.json","paper":"https://pith.science/paper/GAIPKFQ4"},"agent_actions":{"view_html":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK","download_json":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK.json","view_paper":"https://pith.science/paper/GAIPKFQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06531&json=true","fetch_graph":"https://pith.science/api/pith-number/GAIPKFQ4IENLYXP6BTZXSQYAXK/graph.json","fetch_events":"https://pith.science/api/pith-number/GAIPKFQ4IENLYXP6BTZXSQYAXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK/action/storage_attestation","attest_author":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK/action/author_attestation","sign_citation":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK/action/citation_signature","submit_replication":"https://pith.science/pith/GAIPKFQ4IENLYXP6BTZXSQYAXK/action/replication_record"}},"created_at":"2026-07-05T12:06:37.747984+00:00","updated_at":"2026-07-05T12:06:37.747984+00:00"}