{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZNY4HOODDR76DFSV47Q67KBQX","short_pith_number":"pith:TZNY4HOO","schema_version":"1.0","canonical_sha256":"9e5b8e1dce18e3ff0cb2af3f0f7d4185dc014d728554578de9a7561766394ec6","source":{"kind":"arxiv","id":"2404.10939","version":1},"attestation_state":"computed","paper":{"title":"More Room for Language: Investigating the Effect of Retrieval on Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Samuel, Lucas Georges Gabriel Charpentier, Sondre Wold","submitted_at":"2024-04-16T22:43:48Z","abstract_excerpt":"Retrieval-augmented language models pose a promising alternative to standard language modeling. During pretraining, these models search in a corpus of documents for contextually relevant information that could aid the language modeling objective. We introduce an 'ideal retrieval' methodology to study these models in a fully controllable setting. We conduct an extensive evaluation to examine how retrieval augmentation affects the behavior of the underlying language model. Among other things, we observe that these models: i) save substantially less world knowledge in their weights, ii) are bette"},"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":"2404.10939","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-16T22:43:48Z","cross_cats_sorted":[],"title_canon_sha256":"206b5c838daf685bf465b0c151655b7823d60416fad18550b4f109d50e7c9774","abstract_canon_sha256":"945039f9d807e96ff3baf82d09faa3490961edd13135a9e9250cc486a44025fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:01.050840Z","signature_b64":"p9Dv49QgAPEXE5r/VUzsXDhrZ22kb8mqu8rZE/5Li+IV5GfAm99ot3YZzskQEPtotJN+ybPdfNTtTLP3iNn9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e5b8e1dce18e3ff0cb2af3f0f7d4185dc014d728554578de9a7561766394ec6","last_reissued_at":"2026-07-05T08:09:01.050376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:01.050376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Room for Language: Investigating the Effect of Retrieval on Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Samuel, Lucas Georges Gabriel Charpentier, Sondre Wold","submitted_at":"2024-04-16T22:43:48Z","abstract_excerpt":"Retrieval-augmented language models pose a promising alternative to standard language modeling. During pretraining, these models search in a corpus of documents for contextually relevant information that could aid the language modeling objective. We introduce an 'ideal retrieval' methodology to study these models in a fully controllable setting. We conduct an extensive evaluation to examine how retrieval augmentation affects the behavior of the underlying language model. Among other things, we observe that these models: i) save substantially less world knowledge in their weights, ii) are bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10939","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/2404.10939/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":"2404.10939","created_at":"2026-07-05T08:09:01.050451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10939v1","created_at":"2026-07-05T08:09:01.050451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10939","created_at":"2026-07-05T08:09:01.050451+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZNY4HOODDR7","created_at":"2026-07-05T08:09:01.050451+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZNY4HOODDR76DFS","created_at":"2026-07-05T08:09:01.050451+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZNY4HOO","created_at":"2026-07-05T08:09:01.050451+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/TZNY4HOODDR76DFSV47Q67KBQX","json":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX.json","graph_json":"https://pith.science/api/pith-number/TZNY4HOODDR76DFSV47Q67KBQX/graph.json","events_json":"https://pith.science/api/pith-number/TZNY4HOODDR76DFSV47Q67KBQX/events.json","paper":"https://pith.science/paper/TZNY4HOO"},"agent_actions":{"view_html":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX","download_json":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX.json","view_paper":"https://pith.science/paper/TZNY4HOO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10939&json=true","fetch_graph":"https://pith.science/api/pith-number/TZNY4HOODDR76DFSV47Q67KBQX/graph.json","fetch_events":"https://pith.science/api/pith-number/TZNY4HOODDR76DFSV47Q67KBQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/action/storage_attestation","attest_author":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/action/author_attestation","sign_citation":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/action/citation_signature","submit_replication":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/action/replication_record"}},"created_at":"2026-07-05T08:09:01.050451+00:00","updated_at":"2026-07-05T08:09:01.050451+00:00"}