{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WZGB4TTCJLVQKMLQXUM4GREU2S","short_pith_number":"pith:WZGB4TTC","schema_version":"1.0","canonical_sha256":"b64c1e4e624aeb053170bd19c34494d493facbccc4d76dfa5565aeb2e67b7df3","source":{"kind":"arxiv","id":"2510.09711","version":2},"attestation_state":"computed","paper":{"title":"ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaoyan Chen, Lingbing Guo, Wenbin Guo, Xin Wang, Zhao Li, Zirui Chen","submitted_at":"2025-10-10T04:36:13Z","abstract_excerpt":"Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing LLM-based methods often struggle to fully exploit structured semantic representations, as the continuous embedding space of pretrained KG models is fundamentally misaligned with the discrete token space of LLMs. This discrepancy hinders effective semantic transfer and limits their performance. To address this challenge, we propose ReaLM, a novel and effective fra"},"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":"2510.09711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T04:36:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ce3bbfdf0deec4378ade6cda2ce24efd54f5b7269f8de8880a13fbf515b7d047","abstract_canon_sha256":"8753c5c39db5d7d94fff0d973e4d590517bdde38dcbed53803e0919e65894db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:45.662513Z","signature_b64":"+3nPfWMmMztOpUiLpOJ5FTOpzASV5gGGqIDkcBrvr5qh0WWs5FqXtRu/DUynp0a4lJcsruE1wFyl+8oiDg02Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64c1e4e624aeb053170bd19c34494d493facbccc4d76dfa5565aeb2e67b7df3","last_reissued_at":"2026-06-03T01:05:45.662014Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:45.662014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaoyan Chen, Lingbing Guo, Wenbin Guo, Xin Wang, Zhao Li, Zirui Chen","submitted_at":"2025-10-10T04:36:13Z","abstract_excerpt":"Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing LLM-based methods often struggle to fully exploit structured semantic representations, as the continuous embedding space of pretrained KG models is fundamentally misaligned with the discrete token space of LLMs. This discrepancy hinders effective semantic transfer and limits their performance. To address this challenge, we propose ReaLM, a novel and effective fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09711","kind":"arxiv","version":2},"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/2510.09711/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":"2510.09711","created_at":"2026-06-03T01:05:45.662074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.09711v2","created_at":"2026-06-03T01:05:45.662074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09711","created_at":"2026-06-03T01:05:45.662074+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZGB4TTCJLVQ","created_at":"2026-06-03T01:05:45.662074+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZGB4TTCJLVQKMLQ","created_at":"2026-06-03T01:05:45.662074+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZGB4TTC","created_at":"2026-06-03T01:05:45.662074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.21649","citing_title":"GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S","json":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S.json","graph_json":"https://pith.science/api/pith-number/WZGB4TTCJLVQKMLQXUM4GREU2S/graph.json","events_json":"https://pith.science/api/pith-number/WZGB4TTCJLVQKMLQXUM4GREU2S/events.json","paper":"https://pith.science/paper/WZGB4TTC"},"agent_actions":{"view_html":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S","download_json":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S.json","view_paper":"https://pith.science/paper/WZGB4TTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.09711&json=true","fetch_graph":"https://pith.science/api/pith-number/WZGB4TTCJLVQKMLQXUM4GREU2S/graph.json","fetch_events":"https://pith.science/api/pith-number/WZGB4TTCJLVQKMLQXUM4GREU2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S/action/storage_attestation","attest_author":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S/action/author_attestation","sign_citation":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S/action/citation_signature","submit_replication":"https://pith.science/pith/WZGB4TTCJLVQKMLQXUM4GREU2S/action/replication_record"}},"created_at":"2026-06-03T01:05:45.662074+00:00","updated_at":"2026-06-03T01:05:45.662074+00:00"}