{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NVUUY674QVM3WJ3P6GTEZ6ZLQ3","short_pith_number":"pith:NVUUY674","schema_version":"1.0","canonical_sha256":"6d694c7bfc8559bb276ff1a64cfb2b86ca779b5ee1feac5f250629e98f5f73b7","source":{"kind":"arxiv","id":"2606.23911","version":1},"attestation_state":"computed","paper":{"title":"Scaling Dense Retrieval with LLM-Annotated Training Data: Structured Mining and Progressive Curriculum for E-Commerce Sponsored Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Brahanyaa Somasundaram, Hong Yao, Isha Shah, Jhalak Nilesh Acharya, Kuang-chih Lee, Kumar Priyam, Md Omar Faruk Rokon, Minuteresa Thomas, Shasvat Desai, Vamsee Tangirala, Vijay Manchi, Vivek Arora","submitted_at":"2026-06-22T20:19:41Z","abstract_excerpt":"How can we generate high-quality training data for dense retrieval models at production scale, without relying on click signals or manual annotation? This question is critical for e-commerce sponsored search, where click-based training suffers from position bias and tail-query sparsity, and manual labeling at the scale of hundreds of millions of query-item pairs is economically infeasible. Our work is driven by the following insight: heterogeneous retrieval systems disagree on most items they retrieve, and this disagreement creates a natural source of structured training signal -- easy positiv"},"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":"2606.23911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T20:19:41Z","cross_cats_sorted":[],"title_canon_sha256":"9a0ecfe49cfb328e30edfb2e76d9cbf074ebe2701cb8130d1a93a77d98a42b75","abstract_canon_sha256":"81552f17c9750f61c36b58b744d6fad9eb6b3a4c481bfd069e89d314f3806251"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:29.986355Z","signature_b64":"VBvWvovhTGvj5L2me9m4swipGOlj0PJHlk67oLNFAA/7SeApO2LdnKtKAWeiLdQxJO12gWgZM5OUAJ1FyUOuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d694c7bfc8559bb276ff1a64cfb2b86ca779b5ee1feac5f250629e98f5f73b7","last_reissued_at":"2026-06-24T00:14:29.985927Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:29.985927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Dense Retrieval with LLM-Annotated Training Data: Structured Mining and Progressive Curriculum for E-Commerce Sponsored Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Brahanyaa Somasundaram, Hong Yao, Isha Shah, Jhalak Nilesh Acharya, Kuang-chih Lee, Kumar Priyam, Md Omar Faruk Rokon, Minuteresa Thomas, Shasvat Desai, Vamsee Tangirala, Vijay Manchi, Vivek Arora","submitted_at":"2026-06-22T20:19:41Z","abstract_excerpt":"How can we generate high-quality training data for dense retrieval models at production scale, without relying on click signals or manual annotation? This question is critical for e-commerce sponsored search, where click-based training suffers from position bias and tail-query sparsity, and manual labeling at the scale of hundreds of millions of query-item pairs is economically infeasible. Our work is driven by the following insight: heterogeneous retrieval systems disagree on most items they retrieve, and this disagreement creates a natural source of structured training signal -- easy positiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23911","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/2606.23911/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":"2606.23911","created_at":"2026-06-24T00:14:29.985994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23911v1","created_at":"2026-06-24T00:14:29.985994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23911","created_at":"2026-06-24T00:14:29.985994+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVUUY674QVM3","created_at":"2026-06-24T00:14:29.985994+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVUUY674QVM3WJ3P","created_at":"2026-06-24T00:14:29.985994+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVUUY674","created_at":"2026-06-24T00:14:29.985994+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/NVUUY674QVM3WJ3P6GTEZ6ZLQ3","json":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3.json","graph_json":"https://pith.science/api/pith-number/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/graph.json","events_json":"https://pith.science/api/pith-number/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/events.json","paper":"https://pith.science/paper/NVUUY674"},"agent_actions":{"view_html":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3","download_json":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3.json","view_paper":"https://pith.science/paper/NVUUY674","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23911&json=true","fetch_graph":"https://pith.science/api/pith-number/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/action/storage_attestation","attest_author":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/action/author_attestation","sign_citation":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/action/citation_signature","submit_replication":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/action/replication_record"}},"created_at":"2026-06-24T00:14:29.985994+00:00","updated_at":"2026-06-24T00:14:29.985994+00:00"}