{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LZGLMVOJ7IEHBBBYQLRGTRF3Q5","short_pith_number":"pith:LZGLMVOJ","canonical_record":{"source":{"id":"2404.07221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-23T00:49:40Z","cross_cats_sorted":["cs.CL","cs.LG","q-fin.GN"],"title_canon_sha256":"652021da7ae585fdfc33c5138be0dc42446f840fa832e544b5f650f7137c16d4","abstract_canon_sha256":"c9e0673ff52047d3ea1e2347a67617c5efde97933c04fd5ae1ee895942eb037c"},"schema_version":"1.0"},"canonical_sha256":"5e4cb655c9fa0870843882e269c4bb8761194096b2cd84d8effe94ed4dcf475f","source":{"kind":"arxiv","id":"2404.07221","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07221","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07221v2","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07221","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"pith_short_12","alias_value":"LZGLMVOJ7IEH","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"pith_short_16","alias_value":"LZGLMVOJ7IEHBBBY","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"pith_short_8","alias_value":"LZGLMVOJ","created_at":"2026-07-05T08:50:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LZGLMVOJ7IEHBBBYQLRGTRF3Q5","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-23T00:49:40Z","cross_cats_sorted":["cs.CL","cs.LG","q-fin.GN"],"title_canon_sha256":"652021da7ae585fdfc33c5138be0dc42446f840fa832e544b5f650f7137c16d4","abstract_canon_sha256":"c9e0673ff52047d3ea1e2347a67617c5efde97933c04fd5ae1ee895942eb037c"},"schema_version":"1.0"},"canonical_sha256":"5e4cb655c9fa0870843882e269c4bb8761194096b2cd84d8effe94ed4dcf475f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:55.568620Z","signature_b64":"mOYEUHWgoGXDFGM3Ga7lPavtkFH98VjhXO25qlxGztCrQuCEu4p5eZKio6F/ybN8a7zDrhIAeV+Jv3vpje3mAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4cb655c9fa0870843882e269c4bb8761194096b2cd84d8effe94ed4dcf475f","last_reissued_at":"2026-07-05T08:50:55.568081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:55.568081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07221","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:50:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GIIP3J1chBjRcfDOvxGd3W9CekJe8lrCkPMmJbwAVRSwIznVeN1CzzNS4Kax0tBboFOmh7jYmskt6qQTeA5CCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:00:04.362482Z"},"content_sha256":"b1a4faf2542dcaac5de145d1d7a3bb35db93c78e6e546f77bf54819a3f037d63","schema_version":"1.0","event_id":"sha256:b1a4faf2542dcaac5de145d1d7a3bb35db93c78e6e546f77bf54819a3f037d63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LZGLMVOJ7IEHBBBYQLRGTRF3Q5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","q-fin.GN"],"primary_cat":"cs.IR","authors_text":"Alyssa Lee, Eden Chung, Harsh Thakkar, Natan Vidra, Spurthi Setty","submitted_at":"2024-03-23T00:49:40Z","abstract_excerpt":"The effectiveness of Large Language Models (LLMs) in generating accurate responses relies heavily on the quality of input provided, particularly when employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by sourcing the most relevant text chunk(s) to base queries upon. Despite the significant advancements in LLMs' response quality in recent years, users may still encounter inaccuracies or irrelevant answers; these issues often stem from suboptimal text chunk retrieval by RAG rather than the inherent capabilities of LLMs. To augment the efficacy of LLMs, it is crucial to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07221","kind":"arxiv","version":2},"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/2404.07221/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":"2026-07-05T08:50:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNeiHN+P1La2xQbowrULOLKGOdRTq0iWSabzh0J74zaWbqe7VocCINzVHt2wzauZi4wH2WJQVtY5EOuZSJlwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:00:04.363497Z"},"content_sha256":"e47c95b19b7c02fdda063d7b2f6e699d60d930c43086171df127245ece4342bb","schema_version":"1.0","event_id":"sha256:e47c95b19b7c02fdda063d7b2f6e699d60d930c43086171df127245ece4342bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZGLMVOJ7IEHBBBYQLRGTRF3Q5/bundle.json","state_url":"https://pith.science/pith/LZGLMVOJ7IEHBBBYQLRGTRF3Q5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZGLMVOJ7IEHBBBYQLRGTRF3Q5/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":"2026-08-04T21:00:04Z","links":{"resolver":"https://pith.science/pith/LZGLMVOJ7IEHBBBYQLRGTRF3Q5","bundle":"https://pith.science/pith/LZGLMVOJ7IEHBBBYQLRGTRF3Q5/bundle.json","state":"https://pith.science/pith/LZGLMVOJ7IEHBBBYQLRGTRF3Q5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZGLMVOJ7IEHBBBYQLRGTRF3Q5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZGLMVOJ7IEHBBBYQLRGTRF3Q5","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":"c9e0673ff52047d3ea1e2347a67617c5efde97933c04fd5ae1ee895942eb037c","cross_cats_sorted":["cs.CL","cs.LG","q-fin.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-23T00:49:40Z","title_canon_sha256":"652021da7ae585fdfc33c5138be0dc42446f840fa832e544b5f650f7137c16d4"},"schema_version":"1.0","source":{"id":"2404.07221","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07221","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07221v2","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07221","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"pith_short_12","alias_value":"LZGLMVOJ7IEH","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"pith_short_16","alias_value":"LZGLMVOJ7IEHBBBY","created_at":"2026-07-05T08:50:55Z"},{"alias_kind":"pith_short_8","alias_value":"LZGLMVOJ","created_at":"2026-07-05T08:50:55Z"}],"graph_snapshots":[{"event_id":"sha256:e47c95b19b7c02fdda063d7b2f6e699d60d930c43086171df127245ece4342bb","target":"graph","created_at":"2026-07-05T08:50:55Z","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/2404.07221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effectiveness of Large Language Models (LLMs) in generating accurate responses relies heavily on the quality of input provided, particularly when employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by sourcing the most relevant text chunk(s) to base queries upon. Despite the significant advancements in LLMs' response quality in recent years, users may still encounter inaccuracies or irrelevant answers; these issues often stem from suboptimal text chunk retrieval by RAG rather than the inherent capabilities of LLMs. To augment the efficacy of LLMs, it is crucial to ","authors_text":"Alyssa Lee, Eden Chung, Harsh Thakkar, Natan Vidra, Spurthi Setty","cross_cats":["cs.CL","cs.LG","q-fin.GN"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-23T00:49:40Z","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07221","kind":"arxiv","version":2},"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:b1a4faf2542dcaac5de145d1d7a3bb35db93c78e6e546f77bf54819a3f037d63","target":"record","created_at":"2026-07-05T08:50:55Z","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":"c9e0673ff52047d3ea1e2347a67617c5efde97933c04fd5ae1ee895942eb037c","cross_cats_sorted":["cs.CL","cs.LG","q-fin.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-23T00:49:40Z","title_canon_sha256":"652021da7ae585fdfc33c5138be0dc42446f840fa832e544b5f650f7137c16d4"},"schema_version":"1.0","source":{"id":"2404.07221","kind":"arxiv","version":2}},"canonical_sha256":"5e4cb655c9fa0870843882e269c4bb8761194096b2cd84d8effe94ed4dcf475f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e4cb655c9fa0870843882e269c4bb8761194096b2cd84d8effe94ed4dcf475f","first_computed_at":"2026-07-05T08:50:55.568081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:55.568081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mOYEUHWgoGXDFGM3Ga7lPavtkFH98VjhXO25qlxGztCrQuCEu4p5eZKio6F/ybN8a7zDrhIAeV+Jv3vpje3mAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:55.568620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07221","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1a4faf2542dcaac5de145d1d7a3bb35db93c78e6e546f77bf54819a3f037d63","sha256:e47c95b19b7c02fdda063d7b2f6e699d60d930c43086171df127245ece4342bb"],"state_sha256":"3210612cedcec72e3bd15811f0c5408dc338ed73290a664fdf5ee65cfab1deac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yY/Vx+aa4BXFhPdC8OmzfFqDo3h5Uw/Bj1fj5P4KMUdEQr6wAYrfKT6bugJUjNpxJ9vgcYpf4D4gsi1haRHUAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:00:04.371315Z","bundle_sha256":"ebae08bc54848a98379a8e508216520776134afa187c3931a8696eddde745527"}}