{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DDMRV2P4T4Z2VZQBHXEE25UNIL","short_pith_number":"pith:DDMRV2P4","canonical_record":{"source":{"id":"2404.05825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-08T19:29:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6135962b183e3dd5ad8d2ae9f3a6b0006a3e6585a353948f825188b481570288","abstract_canon_sha256":"0777e4f0beb01b401f5dc553e00d201baea43bca964efd0e957fc3653f651027"},"schema_version":"1.0"},"canonical_sha256":"18d91ae9fc9f33aae6013dc84d768d42d9ae3aecab9be702f6ce359c73026cf9","source":{"kind":"arxiv","id":"2404.05825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05825","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05825v1","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05825","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"DDMRV2P4T4Z2","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"DDMRV2P4T4Z2VZQB","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"DDMRV2P4","created_at":"2026-07-05T08:06:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DDMRV2P4T4Z2VZQBHXEE25UNIL","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-08T19:29:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6135962b183e3dd5ad8d2ae9f3a6b0006a3e6585a353948f825188b481570288","abstract_canon_sha256":"0777e4f0beb01b401f5dc553e00d201baea43bca964efd0e957fc3653f651027"},"schema_version":"1.0"},"canonical_sha256":"18d91ae9fc9f33aae6013dc84d768d42d9ae3aecab9be702f6ce359c73026cf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:00.034544Z","signature_b64":"VGGjGvhs8fduK6h3EtTFl9anAbW/U/3HHtyjfqup3LVTONN/d3/lhds488sgqZeElhrdgplIOjr0QK80qtEsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18d91ae9fc9f33aae6013dc84d768d42d9ae3aecab9be702f6ce359c73026cf9","last_reissued_at":"2026-07-05T08:06:00.034130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:00.034130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05825","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":"2026-07-05T08:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVYynCK9v5bTdlM/UrBH07R8cdF6kLK5dLwm4d1ZEOQjtJKB5gCMxDLtPVtjFcaapVGbe9OG+/dYXzpqGBGyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:09:38.873472Z"},"content_sha256":"e126d88e835faab6a0cc501144571a8ccb621366e8121ca8242a1d09c81114b6","schema_version":"1.0","event_id":"sha256:e126d88e835faab6a0cc501144571a8ccb621366e8121ca8242a1d09c81114b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DDMRV2P4T4Z2VZQBHXEE25UNIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Mingrui Wu, Sheng Cao","submitted_at":"2024-04-08T19:29:07Z","abstract_excerpt":"Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large language model (LLM) augmentation. In addition, it also improves some important components in the retrieval model training process, such as negative sampling, loss function, etc. By implementing this LLM-augmented retrieval framework, we have been able to significantly improve the effectiveness of widely-used retriever models such as Bi-encoders (Contriever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05825","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/2404.05825/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":"2026-07-05T08:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Py0lM2oF2iSJwKCUwQcIUfSBWhs9NoS56+H/pdG/ZZHLML47vBkYQr9wShNzRcA0Ej4xCNWLS/Cfx6Rz+sDxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:09:38.874380Z"},"content_sha256":"991cf2b8af6001621aea6bb0812d6083a0ce8bbae417f238dc98e002ec5d6eb9","schema_version":"1.0","event_id":"sha256:991cf2b8af6001621aea6bb0812d6083a0ce8bbae417f238dc98e002ec5d6eb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDMRV2P4T4Z2VZQBHXEE25UNIL/bundle.json","state_url":"https://pith.science/pith/DDMRV2P4T4Z2VZQBHXEE25UNIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDMRV2P4T4Z2VZQBHXEE25UNIL/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":"2026-08-04T05:09:38Z","links":{"resolver":"https://pith.science/pith/DDMRV2P4T4Z2VZQBHXEE25UNIL","bundle":"https://pith.science/pith/DDMRV2P4T4Z2VZQBHXEE25UNIL/bundle.json","state":"https://pith.science/pith/DDMRV2P4T4Z2VZQBHXEE25UNIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDMRV2P4T4Z2VZQBHXEE25UNIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DDMRV2P4T4Z2VZQBHXEE25UNIL","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":"0777e4f0beb01b401f5dc553e00d201baea43bca964efd0e957fc3653f651027","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-08T19:29:07Z","title_canon_sha256":"6135962b183e3dd5ad8d2ae9f3a6b0006a3e6585a353948f825188b481570288"},"schema_version":"1.0","source":{"id":"2404.05825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05825","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05825v1","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05825","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"DDMRV2P4T4Z2","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"DDMRV2P4T4Z2VZQB","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"DDMRV2P4","created_at":"2026-07-05T08:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:991cf2b8af6001621aea6bb0812d6083a0ce8bbae417f238dc98e002ec5d6eb9","target":"graph","created_at":"2026-07-05T08:06:00Z","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/2404.05825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large language model (LLM) augmentation. In addition, it also improves some important components in the retrieval model training process, such as negative sampling, loss function, etc. By implementing this LLM-augmented retrieval framework, we have been able to significantly improve the effectiveness of widely-used retriever models such as Bi-encoders (Contriever","authors_text":"Mingrui Wu, Sheng Cao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-08T19:29:07Z","title":"LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05825","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:e126d88e835faab6a0cc501144571a8ccb621366e8121ca8242a1d09c81114b6","target":"record","created_at":"2026-07-05T08:06:00Z","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":"0777e4f0beb01b401f5dc553e00d201baea43bca964efd0e957fc3653f651027","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-08T19:29:07Z","title_canon_sha256":"6135962b183e3dd5ad8d2ae9f3a6b0006a3e6585a353948f825188b481570288"},"schema_version":"1.0","source":{"id":"2404.05825","kind":"arxiv","version":1}},"canonical_sha256":"18d91ae9fc9f33aae6013dc84d768d42d9ae3aecab9be702f6ce359c73026cf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18d91ae9fc9f33aae6013dc84d768d42d9ae3aecab9be702f6ce359c73026cf9","first_computed_at":"2026-07-05T08:06:00.034130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:00.034130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VGGjGvhs8fduK6h3EtTFl9anAbW/U/3HHtyjfqup3LVTONN/d3/lhds488sgqZeElhrdgplIOjr0QK80qtEsDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:00.034544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e126d88e835faab6a0cc501144571a8ccb621366e8121ca8242a1d09c81114b6","sha256:991cf2b8af6001621aea6bb0812d6083a0ce8bbae417f238dc98e002ec5d6eb9"],"state_sha256":"bdbdbfb342b11dc575711328b82939af06fe4b2e31821d2bca28f191ee97aef9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z01ImTeL9NBsTJyoZR+Kv6B+FHrcOqARtvcIYB1pMZBn/lSOI+804gqQiGLqCmcwq3xe1zJQkhEqmMIcQ6zXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:09:38.879570Z","bundle_sha256":"7c0ec2ef45dd80315e60c1395786a18abfde1fb779947e36ffec31ce43fc9317"}}