{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UJLCVK7IAXL7WCV77JRMVR5WYN","short_pith_number":"pith:UJLCVK7I","schema_version":"1.0","canonical_sha256":"a2562aabe805d7fb0abffa62cac7b6c37e307068cccf9fe0da6c556d7c67c910","source":{"kind":"arxiv","id":"2506.23662","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jie Yang, Philip Lippmann","submitted_at":"2025-06-30T09:38:50Z","abstract_excerpt":"Context-aware embedding methods boost retrieval accuracy by conditioning on corpus statistics (e.g., term co-occurrence and topical patterns) extracted from neighboring documents. However, this context-aware approach requires access to the target corpus or requires domain-specific finetuning, posing practical barriers in privacy-sensitive or resource-constrained settings. We present ZEST, a zero-shot contextual adaptation framework that replaces real corpus access with a one-time offline synthesis of a compact proxy. Given only a handful exemplar documents representative of the general target "},"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":"2506.23662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T09:38:50Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b1787a0fac81afa7d85a84f2058b2c92d47f5b1ef20963360b679bbd49fdbf64","abstract_canon_sha256":"8a2454785db50457c61870143a4f7861f973cb145694b7ebf5ce181a6dff6169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:25.930283Z","signature_b64":"aEZnzpMC0ARY2aNkTtpXVvkHaG+Qzrl8Wm+6h8JcZaVqEwCaaneIynXNEH1QZ1uUM3mnVsNUs+VAMarHlfQjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2562aabe805d7fb0abffa62cac7b6c37e307068cccf9fe0da6c556d7c67c910","last_reissued_at":"2026-07-05T11:29:25.929813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:25.929813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jie Yang, Philip Lippmann","submitted_at":"2025-06-30T09:38:50Z","abstract_excerpt":"Context-aware embedding methods boost retrieval accuracy by conditioning on corpus statistics (e.g., term co-occurrence and topical patterns) extracted from neighboring documents. However, this context-aware approach requires access to the target corpus or requires domain-specific finetuning, posing practical barriers in privacy-sensitive or resource-constrained settings. We present ZEST, a zero-shot contextual adaptation framework that replaces real corpus access with a one-time offline synthesis of a compact proxy. Given only a handful exemplar documents representative of the general target "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23662","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/2506.23662/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":"2506.23662","created_at":"2026-07-05T11:29:25.929872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23662v1","created_at":"2026-07-05T11:29:25.929872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23662","created_at":"2026-07-05T11:29:25.929872+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJLCVK7IAXL7","created_at":"2026-07-05T11:29:25.929872+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJLCVK7IAXL7WCV7","created_at":"2026-07-05T11:29:25.929872+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJLCVK7I","created_at":"2026-07-05T11:29:25.929872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN","json":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN.json","graph_json":"https://pith.science/api/pith-number/UJLCVK7IAXL7WCV77JRMVR5WYN/graph.json","events_json":"https://pith.science/api/pith-number/UJLCVK7IAXL7WCV77JRMVR5WYN/events.json","paper":"https://pith.science/paper/UJLCVK7I"},"agent_actions":{"view_html":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN","download_json":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN.json","view_paper":"https://pith.science/paper/UJLCVK7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23662&json=true","fetch_graph":"https://pith.science/api/pith-number/UJLCVK7IAXL7WCV77JRMVR5WYN/graph.json","fetch_events":"https://pith.science/api/pith-number/UJLCVK7IAXL7WCV77JRMVR5WYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN/action/storage_attestation","attest_author":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN/action/author_attestation","sign_citation":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN/action/citation_signature","submit_replication":"https://pith.science/pith/UJLCVK7IAXL7WCV77JRMVR5WYN/action/replication_record"}},"created_at":"2026-07-05T11:29:25.929872+00:00","updated_at":"2026-07-05T11:29:25.929872+00:00"}