{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SEZOY5QUMTU363BWFUCAZQSAWI","short_pith_number":"pith:SEZOY5QU","canonical_record":{"source":{"id":"2209.05555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-12T19:15:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"39ca5689a088e7923a8e0173fe47f6bc5ccf0ae0e8e116d1c0b7d0aed0f3480c","abstract_canon_sha256":"19f8780283930e301b5865727979587cb5d51844dfe54c41f175552683b34b06"},"schema_version":"1.0"},"canonical_sha256":"9132ec761464e9bf6c362d040cc240b2287f99f878c4cd0c948a27053bc26d13","source":{"kind":"arxiv","id":"2209.05555","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.05555","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"arxiv_version","alias_value":"2209.05555v1","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05555","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"pith_short_12","alias_value":"SEZOY5QUMTU3","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"pith_short_16","alias_value":"SEZOY5QUMTU363BW","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"pith_short_8","alias_value":"SEZOY5QU","created_at":"2026-07-05T04:56:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SEZOY5QUMTU363BWFUCAZQSAWI","target":"record","payload":{"canonical_record":{"source":{"id":"2209.05555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-12T19:15:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"39ca5689a088e7923a8e0173fe47f6bc5ccf0ae0e8e116d1c0b7d0aed0f3480c","abstract_canon_sha256":"19f8780283930e301b5865727979587cb5d51844dfe54c41f175552683b34b06"},"schema_version":"1.0"},"canonical_sha256":"9132ec761464e9bf6c362d040cc240b2287f99f878c4cd0c948a27053bc26d13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:56:47.333377Z","signature_b64":"wQZidVq0KJO/8YGGif31pX33UMdzFq7wWo6kz8C13+PxJcWWko+6lraPDPi1lnseU1glewzbxjds6KzuW4lBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9132ec761464e9bf6c362d040cc240b2287f99f878c4cd0c948a27053bc26d13","last_reissued_at":"2026-07-05T04:56:47.332907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:56:47.332907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.05555","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":"2026-07-05T04:56:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIFelDgWzVRSm3bkCczle2Aaar4uZVfVuMA3KEbVrkbm9MCAsIloOVsw0Ld3LYcLLGdC3CM8V34uK7efLHprAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:02:13.385956Z"},"content_sha256":"e644dc74cdb2070c396fcabcc1f5f31cd4187ac92f1bfe59cfee3ae848bca606","schema_version":"1.0","event_id":"sha256:e644dc74cdb2070c396fcabcc1f5f31cd4187ac92f1bfe59cfee3ae848bca606"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SEZOY5QUMTU363BWFUCAZQSAWI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Embedding-Based Grocery Search Model at Instacart","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Esther Vasiete, Guanghua Shu, Haixun Wang, Saurav Manchanda, Taesik Na, Tejaswi Tenneti, Xiao Xiao, Young Rao, Yuqing Xie, Zhihong Xu","submitted_at":"2022-09-12T19:15:01Z","abstract_excerpt":"The key to e-commerce search is how to best utilize the large yet noisy log data. In this paper, we present our embedding-based model for grocery search at Instacart. The system learns query and product representations with a two-tower transformer-based encoder architecture. To tackle the cold-start problem, we focus on content-based features. To train the model efficiently on noisy data, we propose a self-adversarial learning method and a cascade training method. AccOn an offline human evaluation dataset, we achieve 10% relative improvement in RECALL@20, and for online A/B testing, we achieve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05555","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/2209.05555/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":"2026-07-05T04:56:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3x7kgIXdwlA9GaCldNx9lEOedm+Doi4yMLdENkhrLhO7mxHILCPquoRE+jv+L9wrX99r1Gi3c174H/Wky4OAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:02:13.386337Z"},"content_sha256":"15dede71d986eeb47bf9a36958aeec7dcc9fd2f3994f915ffa666b9845dae743","schema_version":"1.0","event_id":"sha256:15dede71d986eeb47bf9a36958aeec7dcc9fd2f3994f915ffa666b9845dae743"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SEZOY5QUMTU363BWFUCAZQSAWI/bundle.json","state_url":"https://pith.science/pith/SEZOY5QUMTU363BWFUCAZQSAWI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SEZOY5QUMTU363BWFUCAZQSAWI/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":"2026-07-06T07:02:13Z","links":{"resolver":"https://pith.science/pith/SEZOY5QUMTU363BWFUCAZQSAWI","bundle":"https://pith.science/pith/SEZOY5QUMTU363BWFUCAZQSAWI/bundle.json","state":"https://pith.science/pith/SEZOY5QUMTU363BWFUCAZQSAWI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SEZOY5QUMTU363BWFUCAZQSAWI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SEZOY5QUMTU363BWFUCAZQSAWI","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":"19f8780283930e301b5865727979587cb5d51844dfe54c41f175552683b34b06","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-12T19:15:01Z","title_canon_sha256":"39ca5689a088e7923a8e0173fe47f6bc5ccf0ae0e8e116d1c0b7d0aed0f3480c"},"schema_version":"1.0","source":{"id":"2209.05555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.05555","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"arxiv_version","alias_value":"2209.05555v1","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05555","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"pith_short_12","alias_value":"SEZOY5QUMTU3","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"pith_short_16","alias_value":"SEZOY5QUMTU363BW","created_at":"2026-07-05T04:56:47Z"},{"alias_kind":"pith_short_8","alias_value":"SEZOY5QU","created_at":"2026-07-05T04:56:47Z"}],"graph_snapshots":[{"event_id":"sha256:15dede71d986eeb47bf9a36958aeec7dcc9fd2f3994f915ffa666b9845dae743","target":"graph","created_at":"2026-07-05T04:56:47Z","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/2209.05555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The key to e-commerce search is how to best utilize the large yet noisy log data. In this paper, we present our embedding-based model for grocery search at Instacart. The system learns query and product representations with a two-tower transformer-based encoder architecture. To tackle the cold-start problem, we focus on content-based features. To train the model efficiently on noisy data, we propose a self-adversarial learning method and a cascade training method. AccOn an offline human evaluation dataset, we achieve 10% relative improvement in RECALL@20, and for online A/B testing, we achieve","authors_text":"Esther Vasiete, Guanghua Shu, Haixun Wang, Saurav Manchanda, Taesik Na, Tejaswi Tenneti, Xiao Xiao, Young Rao, Yuqing Xie, Zhihong Xu","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-12T19:15:01Z","title":"An Embedding-Based Grocery Search Model at Instacart"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05555","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:e644dc74cdb2070c396fcabcc1f5f31cd4187ac92f1bfe59cfee3ae848bca606","target":"record","created_at":"2026-07-05T04:56:47Z","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":"19f8780283930e301b5865727979587cb5d51844dfe54c41f175552683b34b06","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-12T19:15:01Z","title_canon_sha256":"39ca5689a088e7923a8e0173fe47f6bc5ccf0ae0e8e116d1c0b7d0aed0f3480c"},"schema_version":"1.0","source":{"id":"2209.05555","kind":"arxiv","version":1}},"canonical_sha256":"9132ec761464e9bf6c362d040cc240b2287f99f878c4cd0c948a27053bc26d13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9132ec761464e9bf6c362d040cc240b2287f99f878c4cd0c948a27053bc26d13","first_computed_at":"2026-07-05T04:56:47.332907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:56:47.332907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wQZidVq0KJO/8YGGif31pX33UMdzFq7wWo6kz8C13+PxJcWWko+6lraPDPi1lnseU1glewzbxjds6KzuW4lBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:56:47.333377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.05555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e644dc74cdb2070c396fcabcc1f5f31cd4187ac92f1bfe59cfee3ae848bca606","sha256:15dede71d986eeb47bf9a36958aeec7dcc9fd2f3994f915ffa666b9845dae743"],"state_sha256":"87db2e0718f95cce9c5fb0e8197afb1473d3f9b8998e3afa2c221b2984190d5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SsTAPd7tGy0kxFH7EWcJyYxB/20MfoJNezogD25U1REBz1hOE0oGg861eH06VYiqBXENI50r6XP9lz+t8cPfBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T07:02:13.388434Z","bundle_sha256":"fd67065c65047bc4ba9f5ef608420778a04483f69e9c6b2c751799c04d48ac0e"}}