{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LBBAWW5GXVBZANUUFIFLMXASWJ","short_pith_number":"pith:LBBAWW5G","canonical_record":{"source":{"id":"2402.18031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-28T03:58:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc4e4ef4ec5cc1db5339dde77072f421c5e90968f5c3ae3ad6b6f1267fdebd1e","abstract_canon_sha256":"2b66010df274ec66f25c6ce189fab17cc89b96ae3a081510e9374302d7520104"},"schema_version":"1.0"},"canonical_sha256":"58420b5ba6bd439036942a0ab65c12b241acff63d82864256d3c687fa5afab1c","source":{"kind":"arxiv","id":"2402.18031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18031","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18031v1","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18031","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_12","alias_value":"LBBAWW5GXVBZ","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_16","alias_value":"LBBAWW5GXVBZANUU","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_8","alias_value":"LBBAWW5G","created_at":"2026-07-05T07:50:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LBBAWW5GXVBZANUUFIFLMXASWJ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-28T03:58:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc4e4ef4ec5cc1db5339dde77072f421c5e90968f5c3ae3ad6b6f1267fdebd1e","abstract_canon_sha256":"2b66010df274ec66f25c6ce189fab17cc89b96ae3a081510e9374302d7520104"},"schema_version":"1.0"},"canonical_sha256":"58420b5ba6bd439036942a0ab65c12b241acff63d82864256d3c687fa5afab1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:11.054071Z","signature_b64":"hR33oN5Jj2xd5COkh7AxBYNwju21TUTe0uNT8gzsNm7uKYxW7p5Wa8QCPH8unUQst11RLEkFPiLWA6I/hO5zCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58420b5ba6bd439036942a0ab65c12b241acff63d82864256d3c687fa5afab1c","last_reissued_at":"2026-07-05T07:50:11.053596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:11.053596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18031","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":"2026-07-05T07:50:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kRr/WcdVAbQYN5jifVGb5HpbqJaSsQldVllQSNKty/SDxQ3EzhRvlWCL9b1NF+5xy7yDGsWErO331ZW2apLLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:06:26.000269Z"},"content_sha256":"da259503c02234093c5aea6c1dc0815ed0cfb23a0e4498c08fcd0892db3cfa88","schema_version":"1.0","event_id":"sha256:da259503c02234093c5aea6c1dc0815ed0cfb23a0e4498c08fcd0892db3cfa88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LBBAWW5GXVBZANUUFIFLMXASWJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Corpus-Steered Query Expansion with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Tao Shen, Tianyi Zhou, Yibin Lei, Yu Cao","submitted_at":"2024-02-28T03:58:58Z","abstract_excerpt":"Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However, challenges arise from misalignments between the expansions and the retrieval corpus, resulting in issues like hallucinations and outdated information due to the limited intrinsic knowledge of LLMs. Inspired by Pseudo Relevance Feedback (PRF), we introduce Corpus-Steered Query Expansion (CSQE) to promote the incorporation of knowledge embedded within the corpus. CSQE "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18031","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/2402.18031/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":"2026-07-05T07:50:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eyfkUBIbAlKrqmk1II+ZCx5lAG1PDxeDbJuuOjc27OHroK2UFJv2UCRcDpA1FINEFntoYssrHbBZ2sOJhJDyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:06:26.000911Z"},"content_sha256":"b3b9fd24db496012bf670c7553a1536a3cbc3a4acb3ee4a032af10c2ccebe01c","schema_version":"1.0","event_id":"sha256:b3b9fd24db496012bf670c7553a1536a3cbc3a4acb3ee4a032af10c2ccebe01c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBBAWW5GXVBZANUUFIFLMXASWJ/bundle.json","state_url":"https://pith.science/pith/LBBAWW5GXVBZANUUFIFLMXASWJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBBAWW5GXVBZANUUFIFLMXASWJ/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":"2026-08-08T20:06:26Z","links":{"resolver":"https://pith.science/pith/LBBAWW5GXVBZANUUFIFLMXASWJ","bundle":"https://pith.science/pith/LBBAWW5GXVBZANUUFIFLMXASWJ/bundle.json","state":"https://pith.science/pith/LBBAWW5GXVBZANUUFIFLMXASWJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBBAWW5GXVBZANUUFIFLMXASWJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LBBAWW5GXVBZANUUFIFLMXASWJ","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":"2b66010df274ec66f25c6ce189fab17cc89b96ae3a081510e9374302d7520104","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-28T03:58:58Z","title_canon_sha256":"bc4e4ef4ec5cc1db5339dde77072f421c5e90968f5c3ae3ad6b6f1267fdebd1e"},"schema_version":"1.0","source":{"id":"2402.18031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18031","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18031v1","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18031","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_12","alias_value":"LBBAWW5GXVBZ","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_16","alias_value":"LBBAWW5GXVBZANUU","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_8","alias_value":"LBBAWW5G","created_at":"2026-07-05T07:50:11Z"}],"graph_snapshots":[{"event_id":"sha256:b3b9fd24db496012bf670c7553a1536a3cbc3a4acb3ee4a032af10c2ccebe01c","target":"graph","created_at":"2026-07-05T07:50:11Z","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/2402.18031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However, challenges arise from misalignments between the expansions and the retrieval corpus, resulting in issues like hallucinations and outdated information due to the limited intrinsic knowledge of LLMs. Inspired by Pseudo Relevance Feedback (PRF), we introduce Corpus-Steered Query Expansion (CSQE) to promote the incorporation of knowledge embedded within the corpus. CSQE ","authors_text":"Andrew Yates, Tao Shen, Tianyi Zhou, Yibin Lei, Yu Cao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-28T03:58:58Z","title":"Corpus-Steered Query Expansion with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18031","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:da259503c02234093c5aea6c1dc0815ed0cfb23a0e4498c08fcd0892db3cfa88","target":"record","created_at":"2026-07-05T07:50:11Z","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":"2b66010df274ec66f25c6ce189fab17cc89b96ae3a081510e9374302d7520104","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-28T03:58:58Z","title_canon_sha256":"bc4e4ef4ec5cc1db5339dde77072f421c5e90968f5c3ae3ad6b6f1267fdebd1e"},"schema_version":"1.0","source":{"id":"2402.18031","kind":"arxiv","version":1}},"canonical_sha256":"58420b5ba6bd439036942a0ab65c12b241acff63d82864256d3c687fa5afab1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58420b5ba6bd439036942a0ab65c12b241acff63d82864256d3c687fa5afab1c","first_computed_at":"2026-07-05T07:50:11.053596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:11.053596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hR33oN5Jj2xd5COkh7AxBYNwju21TUTe0uNT8gzsNm7uKYxW7p5Wa8QCPH8unUQst11RLEkFPiLWA6I/hO5zCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:11.054071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da259503c02234093c5aea6c1dc0815ed0cfb23a0e4498c08fcd0892db3cfa88","sha256:b3b9fd24db496012bf670c7553a1536a3cbc3a4acb3ee4a032af10c2ccebe01c"],"state_sha256":"d3eb8fd776531eb4c98ec3baf0a90a19fd93d540c267007312c0c8ba2904b5fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+eoF70BDuZohOtu6cHlgE0bik2kzFXTTLVMxiGZMICbEaOrbi9YmFCD2kuUzBECqNoGuXF6JIZm2ioVsvPABDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:06:26.006121Z","bundle_sha256":"61828ce9f3aeab82b7a5669a96f0a5685c7b8d49310023e205456736e29bca5a"}}