{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:25UTICERGAU7RW2E5X2ZWCQB5H","short_pith_number":"pith:25UTICER","canonical_record":{"source":{"id":"2504.14175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T04:32:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e4e70c61730b403104ad1bb8490af9dc19c67f94ca7db792dc9c378a5388c430","abstract_canon_sha256":"6d8fab4366981a64fc92c64bd56b8cd1949fb1279c1659096e5831eab4ed4a21"},"schema_version":"1.0"},"canonical_sha256":"d7693408913029f8db44edf59b0a01e9e493d264266a976338bf136c59afa048","source":{"kind":"arxiv","id":"2504.14175","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14175","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14175v2","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14175","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"25UTICERGAU7","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"25UTICERGAU7RW2E","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"25UTICER","created_at":"2026-07-05T11:15:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:25UTICERGAU7RW2E5X2ZWCQB5H","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T04:32:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e4e70c61730b403104ad1bb8490af9dc19c67f94ca7db792dc9c378a5388c430","abstract_canon_sha256":"6d8fab4366981a64fc92c64bd56b8cd1949fb1279c1659096e5831eab4ed4a21"},"schema_version":"1.0"},"canonical_sha256":"d7693408913029f8db44edf59b0a01e9e493d264266a976338bf136c59afa048","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:46.254847Z","signature_b64":"xFEDiPEpsacHuvE6HRUjaEqmkN4cgEjRtXouWVNFnPwYMW+A6lNHS89TsPbSLnkFri8HMPdXOEpKD6c02XeDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7693408913029f8db44edf59b0a01e9e493d264266a976338bf136c59afa048","last_reissued_at":"2026-07-05T11:15:46.254263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:46.254263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14175","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":"2026-07-05T11:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gk8CW7F144b837wYwbReSLqCAkf4Ldiuu+3CjEahoSva2gnm31MxlWiYdIYbSyENGx7sNqCKrlh17Ptp7itrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T20:23:20.060298Z"},"content_sha256":"a2c7677693ceb71e74a903924f228a0c0a1316a8b5a1b63c4bc7e22899cec045","schema_version":"1.0","event_id":"sha256:a2c7677693ceb71e74a903924f228a0c0a1316a8b5a1b63c4bc7e22899cec045"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:25UTICERGAU7RW2E5X2ZWCQB5H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jaeyoon Jung, Kunwoo Park, Seunghyun Yoon, Yejun Yoon","submitted_at":"2025-04-19T04:32:38Z","abstract_excerpt":"Query expansion methods powered by large language models (LLMs) have demonstrated effectiveness in zero-shot retrieval tasks. These methods assume that LLMs can generate hypothetical documents that, when incorporated into a query vector, enhance the retrieval of real evidence. However, we challenge this assumption by investigating whether knowledge leakage in benchmarks contributes to the observed performance gains. Using fact verification as a testbed, we analyze whether the generated documents contain information entailed by ground-truth evidence and assess their impact on performance. Our f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14175","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/2504.14175/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":"2026-07-05T11:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNcJWkmtEkb7pVjmF1Oj8l4wW9mq51h9r5Z0awlzqB1QL1+ZHQa33M+VTfMRfqijdXsasiWe5ziOF7CjB0L/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T20:23:20.060802Z"},"content_sha256":"4aa25bbf874ae0bddb8f00dbc38d156f2f7b173d75b59c150a2f4c1d89afcbf6","schema_version":"1.0","event_id":"sha256:4aa25bbf874ae0bddb8f00dbc38d156f2f7b173d75b59c150a2f4c1d89afcbf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25UTICERGAU7RW2E5X2ZWCQB5H/bundle.json","state_url":"https://pith.science/pith/25UTICERGAU7RW2E5X2ZWCQB5H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25UTICERGAU7RW2E5X2ZWCQB5H/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":"2026-08-23T20:23:20Z","links":{"resolver":"https://pith.science/pith/25UTICERGAU7RW2E5X2ZWCQB5H","bundle":"https://pith.science/pith/25UTICERGAU7RW2E5X2ZWCQB5H/bundle.json","state":"https://pith.science/pith/25UTICERGAU7RW2E5X2ZWCQB5H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25UTICERGAU7RW2E5X2ZWCQB5H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:25UTICERGAU7RW2E5X2ZWCQB5H","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":"6d8fab4366981a64fc92c64bd56b8cd1949fb1279c1659096e5831eab4ed4a21","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T04:32:38Z","title_canon_sha256":"e4e70c61730b403104ad1bb8490af9dc19c67f94ca7db792dc9c378a5388c430"},"schema_version":"1.0","source":{"id":"2504.14175","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14175","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14175v2","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14175","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"25UTICERGAU7","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"25UTICERGAU7RW2E","created_at":"2026-07-05T11:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"25UTICER","created_at":"2026-07-05T11:15:46Z"}],"graph_snapshots":[{"event_id":"sha256:4aa25bbf874ae0bddb8f00dbc38d156f2f7b173d75b59c150a2f4c1d89afcbf6","target":"graph","created_at":"2026-07-05T11:15:46Z","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/2504.14175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Query expansion methods powered by large language models (LLMs) have demonstrated effectiveness in zero-shot retrieval tasks. These methods assume that LLMs can generate hypothetical documents that, when incorporated into a query vector, enhance the retrieval of real evidence. However, we challenge this assumption by investigating whether knowledge leakage in benchmarks contributes to the observed performance gains. Using fact verification as a testbed, we analyze whether the generated documents contain information entailed by ground-truth evidence and assess their impact on performance. Our f","authors_text":"Jaeyoon Jung, Kunwoo Park, Seunghyun Yoon, Yejun Yoon","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T04:32:38Z","title":"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14175","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:a2c7677693ceb71e74a903924f228a0c0a1316a8b5a1b63c4bc7e22899cec045","target":"record","created_at":"2026-07-05T11:15:46Z","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":"6d8fab4366981a64fc92c64bd56b8cd1949fb1279c1659096e5831eab4ed4a21","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T04:32:38Z","title_canon_sha256":"e4e70c61730b403104ad1bb8490af9dc19c67f94ca7db792dc9c378a5388c430"},"schema_version":"1.0","source":{"id":"2504.14175","kind":"arxiv","version":2}},"canonical_sha256":"d7693408913029f8db44edf59b0a01e9e493d264266a976338bf136c59afa048","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7693408913029f8db44edf59b0a01e9e493d264266a976338bf136c59afa048","first_computed_at":"2026-07-05T11:15:46.254263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:46.254263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xFEDiPEpsacHuvE6HRUjaEqmkN4cgEjRtXouWVNFnPwYMW+A6lNHS89TsPbSLnkFri8HMPdXOEpKD6c02XeDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:46.254847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14175","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2c7677693ceb71e74a903924f228a0c0a1316a8b5a1b63c4bc7e22899cec045","sha256:4aa25bbf874ae0bddb8f00dbc38d156f2f7b173d75b59c150a2f4c1d89afcbf6"],"state_sha256":"997ffb7d22e47452706d0cdd5e8812efd6462f6b07c9291fb9af84d3e25c3827"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLFlvL2VcVNMampmtOxWnI9FU4e//9+Zw86VqalkdUdNcTvE595WH4lNTJPqGnT6HGNXpkLH2FfFFpCrGlOYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T20:23:20.064790Z","bundle_sha256":"a8cebae8d3913db101e6a071cbf46cae0ceb924d6f7ceccb9098f9aeb9488d97"}}