{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NVUUY674QVM3WJ3P6GTEZ6ZLQ3","short_pith_number":"pith:NVUUY674","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"},"canonical_sha256":"6d694c7bfc8559bb276ff1a64cfb2b86ca779b5ee1feac5f250629e98f5f73b7","source":{"kind":"arxiv","id":"2606.23911","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23911","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23911v1","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23911","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"pith_short_12","alias_value":"NVUUY674QVM3","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"pith_short_16","alias_value":"NVUUY674QVM3WJ3P","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"pith_short_8","alias_value":"NVUUY674","created_at":"2026-06-24T00:14:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NVUUY674QVM3WJ3P6GTEZ6ZLQ3","target":"record","payload":{"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"},"canonical_sha256":"6d694c7bfc8559bb276ff1a64cfb2b86ca779b5ee1feac5f250629e98f5f73b7","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"},"source_kind":"arxiv","source_id":"2606.23911","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":"2026-06-24T00:14:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aZpW/X6yfybcc1PgrhX3kQCUZG/nsutAsSwLhPyuhoZDCcys4D5i2mfQDWI05vexcdbMgGGg2wdT1Z0jUs1YAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T01:36:16.564643Z"},"content_sha256":"480d368d824177d8e044aea68cb36a97b45e9447b18dcedb393cd7e96ee6b33c","schema_version":"1.0","event_id":"sha256:480d368d824177d8e044aea68cb36a97b45e9447b18dcedb393cd7e96ee6b33c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NVUUY674QVM3WJ3P6GTEZ6ZLQ3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T00:14:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qw60b1JHRJRGEs8NYJOAUivV/i6f4wFf+XfLGtoQk0289cvf8wE4UuGLrbrie6Y2FLBM1sEbK6t2z1uEaUhmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T01:36:16.565014Z"},"content_sha256":"ba4d495e4a4527cb9b4e19af8a1fa85c7146508d908e81f3a425806e189400cf","schema_version":"1.0","event_id":"sha256:ba4d495e4a4527cb9b4e19af8a1fa85c7146508d908e81f3a425806e189400cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/bundle.json","state_url":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/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":"2026-06-28T01:36:16Z","links":{"resolver":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3","bundle":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/bundle.json","state":"https://pith.science/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVUUY674QVM3WJ3P6GTEZ6ZLQ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NVUUY674QVM3WJ3P6GTEZ6ZLQ3","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":"81552f17c9750f61c36b58b744d6fad9eb6b3a4c481bfd069e89d314f3806251","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T20:19:41Z","title_canon_sha256":"9a0ecfe49cfb328e30edfb2e76d9cbf074ebe2701cb8130d1a93a77d98a42b75"},"schema_version":"1.0","source":{"id":"2606.23911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23911","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23911v1","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23911","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"pith_short_12","alias_value":"NVUUY674QVM3","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"pith_short_16","alias_value":"NVUUY674QVM3WJ3P","created_at":"2026-06-24T00:14:29Z"},{"alias_kind":"pith_short_8","alias_value":"NVUUY674","created_at":"2026-06-24T00:14:29Z"}],"graph_snapshots":[{"event_id":"sha256:ba4d495e4a4527cb9b4e19af8a1fa85c7146508d908e81f3a425806e189400cf","target":"graph","created_at":"2026-06-24T00:14:29Z","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/2606.23911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T20:19:41Z","title":"Scaling Dense Retrieval with LLM-Annotated Training Data: Structured Mining and Progressive Curriculum for E-Commerce Sponsored Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23911","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":"sha256:480d368d824177d8e044aea68cb36a97b45e9447b18dcedb393cd7e96ee6b33c","target":"record","created_at":"2026-06-24T00:14:29Z","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":"81552f17c9750f61c36b58b744d6fad9eb6b3a4c481bfd069e89d314f3806251","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T20:19:41Z","title_canon_sha256":"9a0ecfe49cfb328e30edfb2e76d9cbf074ebe2701cb8130d1a93a77d98a42b75"},"schema_version":"1.0","source":{"id":"2606.23911","kind":"arxiv","version":1}},"canonical_sha256":"6d694c7bfc8559bb276ff1a64cfb2b86ca779b5ee1feac5f250629e98f5f73b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d694c7bfc8559bb276ff1a64cfb2b86ca779b5ee1feac5f250629e98f5f73b7","first_computed_at":"2026-06-24T00:14:29.985927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:29.985927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VBvWvovhTGvj5L2me9m4swipGOlj0PJHlk67oLNFAA/7SeApO2LdnKtKAWeiLdQxJO12gWgZM5OUAJ1FyUOuBg==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:29.986355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:480d368d824177d8e044aea68cb36a97b45e9447b18dcedb393cd7e96ee6b33c","sha256:ba4d495e4a4527cb9b4e19af8a1fa85c7146508d908e81f3a425806e189400cf"],"state_sha256":"fb1bb32d343ced41e542a95aa0874bed7fdb250384645444b0f5896cc86d3ae0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fDGMPoxpeq+IbZn3cq6b1tKdtaloEQ9flX1bl2uKDn0fHFSvb8wupK97rWWXQJGKan2V3Vc6jdKGiFWyaLdPCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T01:36:16.566975Z","bundle_sha256":"f3d8828c176761877636079c032edc13b18ce346beadcfc194e6c5451fef2c77"}}