{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TZNY4HOODDR76DFSV47Q67KBQX","short_pith_number":"pith:TZNY4HOO","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"},"canonical_sha256":"9e5b8e1dce18e3ff0cb2af3f0f7d4185dc014d728554578de9a7561766394ec6","source":{"kind":"arxiv","id":"2404.10939","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TZNY4HOODDR76DFSV47Q67KBQX","target":"record","payload":{"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"},"canonical_sha256":"9e5b8e1dce18e3ff0cb2af3f0f7d4185dc014d728554578de9a7561766394ec6","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"},"source_kind":"arxiv","source_id":"2404.10939","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:09:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h0+mdfvwSgPSp94HV/gzNCFf46ZkJIgYLfKXetggRwgxiVhVL70UTgZlsXRwEwEdEkQoizWhZ1YIDyWMqOJzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:27:51.937940Z"},"content_sha256":"34ea2fe7922b95bd1e502dd4e3bc9ccd15ea7d154ea01ccf58d41ce6b31c101a","schema_version":"1.0","event_id":"sha256:34ea2fe7922b95bd1e502dd4e3bc9ccd15ea7d154ea01ccf58d41ce6b31c101a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TZNY4HOODDR76DFSV47Q67KBQX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:09:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jGQiHJfT/XUEysg2PmSPpgZi+Dpw82i1v+k6FoqyRrTV0SUSkUqD2KmRFD+0ew5ofiiNsaqrOZxTk2rNCkAHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:27:51.938880Z"},"content_sha256":"31f623f91a944317a5067fdc0bffe649dacb8bc62afe73ea3c8f6cb5650a53d9","schema_version":"1.0","event_id":"sha256:31f623f91a944317a5067fdc0bffe649dacb8bc62afe73ea3c8f6cb5650a53d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/bundle.json","state_url":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TZNY4HOODDR76DFSV47Q67KBQX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T15:27:52Z","links":{"resolver":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX","bundle":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/bundle.json","state":"https://pith.science/pith/TZNY4HOODDR76DFSV47Q67KBQX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TZNY4HOODDR76DFSV47Q67KBQX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rinqYByfvFqrGvDquGJYDwvXrHzeHxC6GJt04kUgBcUxf93+9Gs6ne/aIj8OvdTF+xI35PyKZL1+qQOl9R8IDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T15:27:52.003603Z","bundle_sha256":"f3786498913a0cad0d9e20f6ca051063be14e61f275cffcf38a71646c059cabf"}}