{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EI4V2FMTSLXIYEQHFWZYC7SAYN","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":"33472807aa0272b4c8c2bb215b64589cf959ee09c53081a9f69a79db9a13827e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T08:27:27Z","title_canon_sha256":"b2026cea641933523da41a3f245419298ac409758bcd57d5de305bc19a2da68e"},"schema_version":"1.0","source":{"id":"2407.12854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12854","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12854v1","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12854","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"EI4V2FMTSLXI","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"EI4V2FMTSLXIYEQH","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"EI4V2FMT","created_at":"2026-07-05T08:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:033ededaf734b186bbc9af485810d586e053127cf3cb04d52a66c93569ce3acb","target":"graph","created_at":"2026-07-05T08:45:12Z","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/2407.12854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling laws with respect to the amount of training data and the number of parameters allow us to predict the cost-benefit trade-offs of pretraining language models (LMs) in different configurations. In this paper, we consider another dimension of scaling: the amount of data available at inference time. Specifically, we find that increasing the size of the datastore used by a retrieval-based LM monotonically improves language modeling and several downstream tasks without obvious saturation, such that a smaller model augmented with a large datastore outperforms a larger LM-only model on knowled","authors_text":"Akari Asai, Jacqueline He, Luke Zettlemoyer, Pang Wei Koh, Rulin Shao, Sewon Min, Tim Dettmers, Weijia Shi","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T08:27:27Z","title":"Scaling Retrieval-Based Language Models with a Trillion-Token Datastore"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12854","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":"sha256:7df28d7ef5e8edde5ade681727ae706b8a26ce5cfa8c8fe6d82d0b49b3277a77","target":"record","created_at":"2026-07-05T08:45:12Z","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":"33472807aa0272b4c8c2bb215b64589cf959ee09c53081a9f69a79db9a13827e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T08:27:27Z","title_canon_sha256":"b2026cea641933523da41a3f245419298ac409758bcd57d5de305bc19a2da68e"},"schema_version":"1.0","source":{"id":"2407.12854","kind":"arxiv","version":1}},"canonical_sha256":"22395d159392ee8c12072db3817e40c35dc0c46922b445d6e66d369d977c6304","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22395d159392ee8c12072db3817e40c35dc0c46922b445d6e66d369d977c6304","first_computed_at":"2026-07-05T08:45:12.635907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:12.635907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HM2QjybIbNcQV37OIduOTrKdWDQ0RvuYpK95rnWpXxztSDkfAjdfQwjQWIJi4tIQy8FfXzBxe0afIK4N1XyFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:12.636392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7df28d7ef5e8edde5ade681727ae706b8a26ce5cfa8c8fe6d82d0b49b3277a77","sha256:033ededaf734b186bbc9af485810d586e053127cf3cb04d52a66c93569ce3acb"],"state_sha256":"9b5bc21cd63ed780058955df57449ec8d335417a1dc76a43a63259462ae4effb"}