{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3TFIHJJNCEENNPOXGPUWIA7LRY","short_pith_number":"pith:3TFIHJJN","schema_version":"1.0","canonical_sha256":"dcca83a52d1108d6bdd733e96403eb8e2affc23e536f79dfde16718669b72a81","source":{"kind":"arxiv","id":"2201.09680","version":1},"attestation_state":"computed","paper":{"title":"Relational Memory Augmented Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Phil Blunsom, Qi Liu","submitted_at":"2022-01-24T13:25:41Z","abstract_excerpt":"We present a memory-augmented approach to condition an autoregressive language model on a knowledge graph. We represent the graph as a collection of relation triples and retrieve relevant relations for a given context to improve text generation. Experiments on WikiText-103, WMT19, and enwik8 English datasets demonstrate that our approach produces a better language model in terms of perplexity and bits per character. We also show that relational memory improves coherence, is complementary to token-based memory, and enables causal interventions. Our model provides a simple yet effective way to c"},"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":"2201.09680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-24T13:25:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d6f7fe205d9743b0f7996d4862be9f988866ae446fcdd9727da50b76d986d3c","abstract_canon_sha256":"aff709c8aeee07417f2776da43e5645f7c9c010426ac68518a8fc4dfcdc2e7e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:00.037288Z","signature_b64":"pZ+B69n2k7/aMMeKDsB3qi0Hmda40XDLkvLn7r6lBxue7LrrLp0s9jD6ZxsghvYauGeShKDxPl9ELYk3DrjGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcca83a52d1108d6bdd733e96403eb8e2affc23e536f79dfde16718669b72a81","last_reissued_at":"2026-07-05T03:51:00.036908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:00.036908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relational Memory Augmented Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Phil Blunsom, Qi Liu","submitted_at":"2022-01-24T13:25:41Z","abstract_excerpt":"We present a memory-augmented approach to condition an autoregressive language model on a knowledge graph. We represent the graph as a collection of relation triples and retrieve relevant relations for a given context to improve text generation. Experiments on WikiText-103, WMT19, and enwik8 English datasets demonstrate that our approach produces a better language model in terms of perplexity and bits per character. We also show that relational memory improves coherence, is complementary to token-based memory, and enables causal interventions. Our model provides a simple yet effective way to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09680","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/2201.09680/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":"2201.09680","created_at":"2026-07-05T03:51:00.036968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.09680v1","created_at":"2026-07-05T03:51:00.036968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09680","created_at":"2026-07-05T03:51:00.036968+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TFIHJJNCEEN","created_at":"2026-07-05T03:51:00.036968+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TFIHJJNCEENNPOX","created_at":"2026-07-05T03:51:00.036968+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TFIHJJN","created_at":"2026-07-05T03:51:00.036968+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/3TFIHJJNCEENNPOXGPUWIA7LRY","json":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY.json","graph_json":"https://pith.science/api/pith-number/3TFIHJJNCEENNPOXGPUWIA7LRY/graph.json","events_json":"https://pith.science/api/pith-number/3TFIHJJNCEENNPOXGPUWIA7LRY/events.json","paper":"https://pith.science/paper/3TFIHJJN"},"agent_actions":{"view_html":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY","download_json":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY.json","view_paper":"https://pith.science/paper/3TFIHJJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.09680&json=true","fetch_graph":"https://pith.science/api/pith-number/3TFIHJJNCEENNPOXGPUWIA7LRY/graph.json","fetch_events":"https://pith.science/api/pith-number/3TFIHJJNCEENNPOXGPUWIA7LRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY/action/storage_attestation","attest_author":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY/action/author_attestation","sign_citation":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY/action/citation_signature","submit_replication":"https://pith.science/pith/3TFIHJJNCEENNPOXGPUWIA7LRY/action/replication_record"}},"created_at":"2026-07-05T03:51:00.036968+00:00","updated_at":"2026-07-05T03:51:00.036968+00:00"}