{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D5PTCLC4UDUNWXFNT42Z54QB5Z","short_pith_number":"pith:D5PTCLC4","canonical_record":{"source":{"id":"2408.09017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-16T20:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"a470d2e261080ea44565f3f7d6ae8623e8f8b2beca80dd31c5be09e5ca7c44f8","abstract_canon_sha256":"12599045cddb238ad8c20f5a365d9c0fb78112f5db24b9040659f3f9bf6e295d"},"schema_version":"1.0"},"canonical_sha256":"1f5f312c5ca0e8db5cad9f359ef201ee6e764d8e037cb88f12867e963798388f","source":{"kind":"arxiv","id":"2408.09017","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09017","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09017v1","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09017","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"D5PTCLC4UDUN","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"D5PTCLC4UDUNWXFN","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"D5PTCLC4","created_at":"2026-07-05T08:56:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D5PTCLC4UDUNWXFNT42Z54QB5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-16T20:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"a470d2e261080ea44565f3f7d6ae8623e8f8b2beca80dd31c5be09e5ca7c44f8","abstract_canon_sha256":"12599045cddb238ad8c20f5a365d9c0fb78112f5db24b9040659f3f9bf6e295d"},"schema_version":"1.0"},"canonical_sha256":"1f5f312c5ca0e8db5cad9f359ef201ee6e764d8e037cb88f12867e963798388f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:26.799804Z","signature_b64":"e3UfhLq5t5vd1OD6dDrCeLlyzeCAAvM/30ndhHdOByEhoKA8aJJSo8NFgBRn31YEf20wr91/dfBK5owK2WKFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f5f312c5ca0e8db5cad9f359ef201ee6e764d8e037cb88f12867e963798388f","last_reissued_at":"2026-07-05T08:56:26.799376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:26.799376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09017","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":"2026-07-05T08:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OvqAh7u1jdGC1VHDoe1jAwqy5IG18CfHBjh3/LaPfbTtSQtPEAJp1VZyLerRURb6gM1q2hdVqkk4OtrIQzesCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:02:30.041290Z"},"content_sha256":"3dc45e32f40d74ab95054f0296a25572ffaddce2ea998465526d6f37bca5a7ff","schema_version":"1.0","event_id":"sha256:3dc45e32f40d74ab95054f0296a25572ffaddce2ea998465526d6f37bca5a7ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D5PTCLC4UDUNWXFNT42Z54QB5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta Knowledge for Retrieval Augmented Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Adi Banerjee, Florian Felice, Jonathan Taws, Laurent Mombaerts, Tarik Borogovac, Terry Ding","submitted_at":"2024-08-16T20:55:21Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) is a technique used to augment Large Language Models (LLMs) with contextually relevant, time-critical, or domain-specific information without altering the underlying model parameters. However, constructing RAG systems that can effectively synthesize information from large and diverse set of documents remains a significant challenge. We introduce a novel data-centric RAG workflow for LLMs, transforming the traditional retrieve-then-read system into a more advanced prepare-then-rewrite-then-retrieve-then-read framework, to achieve higher domain expert-level u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09017","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/2408.09017/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":"2026-07-05T08:56:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"io5Fg30RCCSi1iQ3PT4qZOQz0a/yQDUAEPjJmt1drQ04A1OavNzzQT8GsvhFnODWJOLASGQ8uWOyqJIoWz+UCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:02:30.042061Z"},"content_sha256":"2734c3c86fc6c135335f9e84cd5032ab30cd92f4b3b6e4994f8dd00a416a4a35","schema_version":"1.0","event_id":"sha256:2734c3c86fc6c135335f9e84cd5032ab30cd92f4b3b6e4994f8dd00a416a4a35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5PTCLC4UDUNWXFNT42Z54QB5Z/bundle.json","state_url":"https://pith.science/pith/D5PTCLC4UDUNWXFNT42Z54QB5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5PTCLC4UDUNWXFNT42Z54QB5Z/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":"2026-08-09T12:02:30Z","links":{"resolver":"https://pith.science/pith/D5PTCLC4UDUNWXFNT42Z54QB5Z","bundle":"https://pith.science/pith/D5PTCLC4UDUNWXFNT42Z54QB5Z/bundle.json","state":"https://pith.science/pith/D5PTCLC4UDUNWXFNT42Z54QB5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5PTCLC4UDUNWXFNT42Z54QB5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D5PTCLC4UDUNWXFNT42Z54QB5Z","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":"12599045cddb238ad8c20f5a365d9c0fb78112f5db24b9040659f3f9bf6e295d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-16T20:55:21Z","title_canon_sha256":"a470d2e261080ea44565f3f7d6ae8623e8f8b2beca80dd31c5be09e5ca7c44f8"},"schema_version":"1.0","source":{"id":"2408.09017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09017","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09017v1","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09017","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_12","alias_value":"D5PTCLC4UDUN","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_16","alias_value":"D5PTCLC4UDUNWXFN","created_at":"2026-07-05T08:56:26Z"},{"alias_kind":"pith_short_8","alias_value":"D5PTCLC4","created_at":"2026-07-05T08:56:26Z"}],"graph_snapshots":[{"event_id":"sha256:2734c3c86fc6c135335f9e84cd5032ab30cd92f4b3b6e4994f8dd00a416a4a35","target":"graph","created_at":"2026-07-05T08:56:26Z","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/2408.09017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval Augmented Generation (RAG) is a technique used to augment Large Language Models (LLMs) with contextually relevant, time-critical, or domain-specific information without altering the underlying model parameters. However, constructing RAG systems that can effectively synthesize information from large and diverse set of documents remains a significant challenge. We introduce a novel data-centric RAG workflow for LLMs, transforming the traditional retrieve-then-read system into a more advanced prepare-then-rewrite-then-retrieve-then-read framework, to achieve higher domain expert-level u","authors_text":"Adi Banerjee, Florian Felice, Jonathan Taws, Laurent Mombaerts, Tarik Borogovac, Terry Ding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-16T20:55:21Z","title":"Meta Knowledge for Retrieval Augmented Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09017","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":"sha256:3dc45e32f40d74ab95054f0296a25572ffaddce2ea998465526d6f37bca5a7ff","target":"record","created_at":"2026-07-05T08:56:26Z","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":"12599045cddb238ad8c20f5a365d9c0fb78112f5db24b9040659f3f9bf6e295d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-16T20:55:21Z","title_canon_sha256":"a470d2e261080ea44565f3f7d6ae8623e8f8b2beca80dd31c5be09e5ca7c44f8"},"schema_version":"1.0","source":{"id":"2408.09017","kind":"arxiv","version":1}},"canonical_sha256":"1f5f312c5ca0e8db5cad9f359ef201ee6e764d8e037cb88f12867e963798388f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f5f312c5ca0e8db5cad9f359ef201ee6e764d8e037cb88f12867e963798388f","first_computed_at":"2026-07-05T08:56:26.799376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:26.799376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e3UfhLq5t5vd1OD6dDrCeLlyzeCAAvM/30ndhHdOByEhoKA8aJJSo8NFgBRn31YEf20wr91/dfBK5owK2WKFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:26.799804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc45e32f40d74ab95054f0296a25572ffaddce2ea998465526d6f37bca5a7ff","sha256:2734c3c86fc6c135335f9e84cd5032ab30cd92f4b3b6e4994f8dd00a416a4a35"],"state_sha256":"42fd21796963447110a1c613b92e1a218d792cc1cbdd6f69c9e5da380944b5e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2fxclcWs/xGJCbNOaMHtwQY6rDAUicS70rOVD6WPq6CwO7+81DP40hglkoydICn5+S+9f/M9nFmH3mrHnl2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:02:30.047616Z","bundle_sha256":"371fb5cd6173becfe4a743985693d8d9189d93ff299e15ea65cc5f8ed953cff9"}}