{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IXCGXKWPTNNSCW37NMUYYQ6Y5U","short_pith_number":"pith:IXCGXKWP","schema_version":"1.0","canonical_sha256":"45c46baacf9b5b215b7f6b298c43d8ed05e72edc39007bb70b40441deea85b90","source":{"kind":"arxiv","id":"2410.21242","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"James Glass, Leslie Shing, Nour Jedidi, Yung-Sung Chuang","submitted_at":"2024-10-28T17:40:40Z","abstract_excerpt":"Building effective dense retrieval systems remains difficult when relevance supervision is not available. Recent work has looked to overcome this challenge by using a Large Language Model (LLM) to generate hypothetical documents that can be used to find the closest real document. However, this approach relies solely on the LLM to have domain-specific knowledge relevant to the query, which may not be practical. Furthermore, generating hypothetical documents can be inefficient as it requires the LLM to generate a large number of tokens for each query. To address these challenges, we introduce Re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.21242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-28T17:40:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"0fb9c492312bf544fa20708188adf50114cfeb283e11b38c0b291d47023d0ecc","abstract_canon_sha256":"43c79ffc44b3358ef6fdcb9b90c5937c1178fe24ee85b6dd31fe5796a5be7451"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:17.385131Z","signature_b64":"OJGfDTldmDESTfARaxl7C9n+3EzzkXLXRTPR/vZkZ72qT3eP6/zmPJPiss5s3wq0+a8PDdq/fydYD32uTvEmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45c46baacf9b5b215b7f6b298c43d8ed05e72edc39007bb70b40441deea85b90","last_reissued_at":"2026-07-05T09:27:17.384695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:17.384695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"James Glass, Leslie Shing, Nour Jedidi, Yung-Sung Chuang","submitted_at":"2024-10-28T17:40:40Z","abstract_excerpt":"Building effective dense retrieval systems remains difficult when relevance supervision is not available. Recent work has looked to overcome this challenge by using a Large Language Model (LLM) to generate hypothetical documents that can be used to find the closest real document. However, this approach relies solely on the LLM to have domain-specific knowledge relevant to the query, which may not be practical. Furthermore, generating hypothetical documents can be inefficient as it requires the LLM to generate a large number of tokens for each query. To address these challenges, we introduce Re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21242","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/2410.21242/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.21242","created_at":"2026-07-05T09:27:17.384751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21242v1","created_at":"2026-07-05T09:27:17.384751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21242","created_at":"2026-07-05T09:27:17.384751+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXCGXKWPTNNS","created_at":"2026-07-05T09:27:17.384751+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXCGXKWPTNNSCW37","created_at":"2026-07-05T09:27:17.384751+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXCGXKWP","created_at":"2026-07-05T09:27:17.384751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15540","citing_title":"MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U","json":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U.json","graph_json":"https://pith.science/api/pith-number/IXCGXKWPTNNSCW37NMUYYQ6Y5U/graph.json","events_json":"https://pith.science/api/pith-number/IXCGXKWPTNNSCW37NMUYYQ6Y5U/events.json","paper":"https://pith.science/paper/IXCGXKWP"},"agent_actions":{"view_html":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U","download_json":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U.json","view_paper":"https://pith.science/paper/IXCGXKWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21242&json=true","fetch_graph":"https://pith.science/api/pith-number/IXCGXKWPTNNSCW37NMUYYQ6Y5U/graph.json","fetch_events":"https://pith.science/api/pith-number/IXCGXKWPTNNSCW37NMUYYQ6Y5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U/action/storage_attestation","attest_author":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U/action/author_attestation","sign_citation":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U/action/citation_signature","submit_replication":"https://pith.science/pith/IXCGXKWPTNNSCW37NMUYYQ6Y5U/action/replication_record"}},"created_at":"2026-07-05T09:27:17.384751+00:00","updated_at":"2026-07-05T09:27:17.384751+00:00"}