{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LGEISFMLO5TFE5535DOHW4QHDX","short_pith_number":"pith:LGEISFML","canonical_record":{"source":{"id":"2508.17400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T15:19:24Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"840f5c4845f89e3b4321e125fff80833690dff6aba2af38f3c026c4b50ecfbcb","abstract_canon_sha256":"a119420a1607ff3e3d1feee562f0b6a09cffcaf236ef63ffc0f1136014a3e3c0"},"schema_version":"1.0"},"canonical_sha256":"598889158b77665277bbe8dc7b72071df6e5ab8dd7e6399f013392be7e254810","source":{"kind":"arxiv","id":"2508.17400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17400","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17400v1","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17400","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"LGEISFMLO5TF","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"LGEISFMLO5TFE553","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"LGEISFML","created_at":"2026-07-05T11:58:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LGEISFMLO5TFE5535DOHW4QHDX","target":"record","payload":{"canonical_record":{"source":{"id":"2508.17400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T15:19:24Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"840f5c4845f89e3b4321e125fff80833690dff6aba2af38f3c026c4b50ecfbcb","abstract_canon_sha256":"a119420a1607ff3e3d1feee562f0b6a09cffcaf236ef63ffc0f1136014a3e3c0"},"schema_version":"1.0"},"canonical_sha256":"598889158b77665277bbe8dc7b72071df6e5ab8dd7e6399f013392be7e254810","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:40.964773Z","signature_b64":"WIZdHSbWWPkrtoLvwnwJpvY+1CPFA0Me94cDSFdKdwiEKJjTgDXR/uLJ57CKroH+0zxomSymVaHYJxut09/WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"598889158b77665277bbe8dc7b72071df6e5ab8dd7e6399f013392be7e254810","last_reissued_at":"2026-07-05T11:58:40.964312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:40.964312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.17400","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":"2026-07-05T11:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"meleqlNNWO6iVXpGiGTALArnYdOa2Z93zLjg//kFRFJ4IzgE3d3hj7+3QDnhyCP94kjDfJFf+bDU4v5SUvjUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:46:16.776531Z"},"content_sha256":"03c9648bff437f09e695c9ace2087151151f5baf388ad1da22ed6cd8981ecded","schema_version":"1.0","event_id":"sha256:03c9648bff437f09e695c9ace2087151151f5baf388ad1da22ed6cd8981ecded"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LGEISFMLO5TFE5535DOHW4QHDX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Connor Jennings, Erica Ji Yuen, Jacob Portes, Michael Carbin, Sasha Doubov","submitted_at":"2025-08-24T15:19:24Z","abstract_excerpt":"How does retrieval performance scale with pretraining FLOPs? We benchmark retrieval performance across LLM model sizes from 125 million parameters to 7 billion parameters pretrained on datasets ranging from 1 billion tokens to more than 2 trillion tokens. We find that retrieval performance on zero-shot BEIR tasks predictably scales with LLM size, training duration, and estimated FLOPs. We also show that In-Context Learning scores are strongly correlated with retrieval scores across retrieval tasks. Finally, we highlight the implications this has for the development of LLM-based retrievers."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17400","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/2508.17400/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":"2026-07-05T11:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mrlqv2Qw0OQcn/ur2ntdiLNcTiw+UivG8A6xgLmanKYw5/xMRR+LPunA37DQI87Y9H5sgF5qjxkb7uEBVmQvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:46:16.777551Z"},"content_sha256":"09199900716cbf55c80a5cbaff810cee6d02dc5c370c2b50bdb51b3bd98e916e","schema_version":"1.0","event_id":"sha256:09199900716cbf55c80a5cbaff810cee6d02dc5c370c2b50bdb51b3bd98e916e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGEISFMLO5TFE5535DOHW4QHDX/bundle.json","state_url":"https://pith.science/pith/LGEISFMLO5TFE5535DOHW4QHDX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGEISFMLO5TFE5535DOHW4QHDX/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":"2026-08-04T04:46:16Z","links":{"resolver":"https://pith.science/pith/LGEISFMLO5TFE5535DOHW4QHDX","bundle":"https://pith.science/pith/LGEISFMLO5TFE5535DOHW4QHDX/bundle.json","state":"https://pith.science/pith/LGEISFMLO5TFE5535DOHW4QHDX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGEISFMLO5TFE5535DOHW4QHDX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LGEISFMLO5TFE5535DOHW4QHDX","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":"a119420a1607ff3e3d1feee562f0b6a09cffcaf236ef63ffc0f1136014a3e3c0","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T15:19:24Z","title_canon_sha256":"840f5c4845f89e3b4321e125fff80833690dff6aba2af38f3c026c4b50ecfbcb"},"schema_version":"1.0","source":{"id":"2508.17400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17400","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17400v1","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17400","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"LGEISFMLO5TF","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"LGEISFMLO5TFE553","created_at":"2026-07-05T11:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"LGEISFML","created_at":"2026-07-05T11:58:40Z"}],"graph_snapshots":[{"event_id":"sha256:09199900716cbf55c80a5cbaff810cee6d02dc5c370c2b50bdb51b3bd98e916e","target":"graph","created_at":"2026-07-05T11:58:40Z","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/2508.17400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How does retrieval performance scale with pretraining FLOPs? We benchmark retrieval performance across LLM model sizes from 125 million parameters to 7 billion parameters pretrained on datasets ranging from 1 billion tokens to more than 2 trillion tokens. We find that retrieval performance on zero-shot BEIR tasks predictably scales with LLM size, training duration, and estimated FLOPs. We also show that In-Context Learning scores are strongly correlated with retrieval scores across retrieval tasks. Finally, we highlight the implications this has for the development of LLM-based retrievers.","authors_text":"Connor Jennings, Erica Ji Yuen, Jacob Portes, Michael Carbin, Sasha Doubov","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T15:19:24Z","title":"Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17400","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":"sha256:03c9648bff437f09e695c9ace2087151151f5baf388ad1da22ed6cd8981ecded","target":"record","created_at":"2026-07-05T11:58:40Z","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":"a119420a1607ff3e3d1feee562f0b6a09cffcaf236ef63ffc0f1136014a3e3c0","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-24T15:19:24Z","title_canon_sha256":"840f5c4845f89e3b4321e125fff80833690dff6aba2af38f3c026c4b50ecfbcb"},"schema_version":"1.0","source":{"id":"2508.17400","kind":"arxiv","version":1}},"canonical_sha256":"598889158b77665277bbe8dc7b72071df6e5ab8dd7e6399f013392be7e254810","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"598889158b77665277bbe8dc7b72071df6e5ab8dd7e6399f013392be7e254810","first_computed_at":"2026-07-05T11:58:40.964312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:40.964312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WIZdHSbWWPkrtoLvwnwJpvY+1CPFA0Me94cDSFdKdwiEKJjTgDXR/uLJ57CKroH+0zxomSymVaHYJxut09/WCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:40.964773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03c9648bff437f09e695c9ace2087151151f5baf388ad1da22ed6cd8981ecded","sha256:09199900716cbf55c80a5cbaff810cee6d02dc5c370c2b50bdb51b3bd98e916e"],"state_sha256":"3661ef7c12ed85c58198d3e96dd3f2fa92fb3fe1260f0355988af623402388d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRmm1wtJ1jGrO6XZP7iS01GpJHNDJAXYyaTEW6rHfXOuG4qfm/YRcdfRIR960olEQkMsZtkFJLHNu0+ddX3FCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:46:16.784687Z","bundle_sha256":"7200cfdc4c80c7527807b8b77ea930f8260c3ca64df4c322fc28dee31d60b850"}}