{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TZNY4HOODDR76DFSV47Q67KBQX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"945039f9d807e96ff3baf82d09faa3490961edd13135a9e9250cc486a44025fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-16T22:43:48Z","title_canon_sha256":"206b5c838daf685bf465b0c151655b7823d60416fad18550b4f109d50e7c9774"},"schema_version":"1.0","source":{"id":"2404.10939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10939","created_at":"2026-07-05T08:09:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10939v1","created_at":"2026-07-05T08:09:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10939","created_at":"2026-07-05T08:09:01Z"},{"alias_kind":"pith_short_12","alias_value":"TZNY4HOODDR7","created_at":"2026-07-05T08:09:01Z"},{"alias_kind":"pith_short_16","alias_value":"TZNY4HOODDR76DFS","created_at":"2026-07-05T08:09:01Z"},{"alias_kind":"pith_short_8","alias_value":"TZNY4HOO","created_at":"2026-07-05T08:09:01Z"}],"graph_snapshots":[{"event_id":"sha256:31f623f91a944317a5067fdc0bffe649dacb8bc62afe73ea3c8f6cb5650a53d9","target":"graph","created_at":"2026-07-05T08:09:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.10939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Samuel, Lucas Georges Gabriel Charpentier, Sondre Wold","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-16T22:43:48Z","title":"More Room for Language: Investigating the Effect of Retrieval on Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10939","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:34ea2fe7922b95bd1e502dd4e3bc9ccd15ea7d154ea01ccf58d41ce6b31c101a","target":"record","created_at":"2026-07-05T08:09:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"945039f9d807e96ff3baf82d09faa3490961edd13135a9e9250cc486a44025fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-16T22:43:48Z","title_canon_sha256":"206b5c838daf685bf465b0c151655b7823d60416fad18550b4f109d50e7c9774"},"schema_version":"1.0","source":{"id":"2404.10939","kind":"arxiv","version":1}},"canonical_sha256":"9e5b8e1dce18e3ff0cb2af3f0f7d4185dc014d728554578de9a7561766394ec6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e5b8e1dce18e3ff0cb2af3f0f7d4185dc014d728554578de9a7561766394ec6","first_computed_at":"2026-07-05T08:09:01.050376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:01.050376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p9Dv49QgAPEXE5r/VUzsXDhrZ22kb8mqu8rZE/5Li+IV5GfAm99ot3YZzskQEPtotJN+ybPdfNTtTLP3iNn9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:01.050840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34ea2fe7922b95bd1e502dd4e3bc9ccd15ea7d154ea01ccf58d41ce6b31c101a","sha256:31f623f91a944317a5067fdc0bffe649dacb8bc62afe73ea3c8f6cb5650a53d9"],"state_sha256":"398d3fac0955a47b836408312a23eff18e72de47425884840c5a8aacaedc9b77"}