{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ODLFK4HIHXS44PZNNG4H657UQR","short_pith_number":"pith:ODLFK4HI","canonical_record":{"source":{"id":"2607.23121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-25T09:41:21Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c14c1663d4035b1729a4c4e15dbed4cd92ed16f2b52af127a4ddcdd67fa2bd08","abstract_canon_sha256":"0235ed4206e8f904949f3b478d2011a87718d332b12c9c49676bbd58b0809ebb"},"schema_version":"1.0"},"canonical_sha256":"70d65570e83de5ce3f2d69b87f77f4846934ae881d83a8b75fcbba1f7649a7d6","source":{"kind":"arxiv","id":"2607.23121","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23121","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23121v1","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23121","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"ODLFK4HIHXS4","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"pith_short_16","alias_value":"ODLFK4HIHXS44PZN","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"pith_short_8","alias_value":"ODLFK4HI","created_at":"2026-07-28T01:22:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ODLFK4HIHXS44PZNNG4H657UQR","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-25T09:41:21Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c14c1663d4035b1729a4c4e15dbed4cd92ed16f2b52af127a4ddcdd67fa2bd08","abstract_canon_sha256":"0235ed4206e8f904949f3b478d2011a87718d332b12c9c49676bbd58b0809ebb"},"schema_version":"1.0"},"canonical_sha256":"70d65570e83de5ce3f2d69b87f77f4846934ae881d83a8b75fcbba1f7649a7d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:07.787297Z","signature_b64":"InuFWrdBGwD+57xnbUYUPHCMo0oIBuMhrQ4ROMxEq71J00psx0vF83OGTRxvGMZIARq/Yq1510W5bOVne8xdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70d65570e83de5ce3f2d69b87f77f4846934ae881d83a8b75fcbba1f7649a7d6","last_reissued_at":"2026-07-28T01:22:07.786541Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:07.786541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23121","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":"2026-07-28T01:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2h/eJqdIBvm/F8wYNf+1xX5E43gws+iSokli3bkrus7JDiJnBsQXkJEP3g94qsbenZSMUGmJpSlxCwjsh1UBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:00:20.210509Z"},"content_sha256":"613ff36dcd4c6ab0f17c89daf76595a281c5f86c7268bb2267820288cab6caa7","schema_version":"1.0","event_id":"sha256:613ff36dcd4c6ab0f17c89daf76595a281c5f86c7268bb2267820288cab6caa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ODLFK4HIHXS44PZNNG4H657UQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Congfei Zhang, Ge Liu, Hsiang-wei Chao, Jinchao Li, Jingxiao Ma, Meghana Missula, Rachel Liao, Shantanu Aggarwal, Siman Wang, Vincent Zhang, Xiao Bai, XiaoDong Liu, Yajun Wang, Yunzhi Zhou, Yu Zhang, Zhe Liu, Zichu Li","submitted_at":"2026-07-25T09:41:21Z","abstract_excerpt":"Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories). While Large Language Models (LLMs) capture semantic intent better than traditional embedding models, deploying them at scale introduces prohibitive inference costs and lexical mismatch issues. Through controlled experiments on millions of users, we demonstrate a critical retrieval decomposition: rule-generated queries excel at retargeting on a lexical BM25 index, while LLM-ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23121","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/2607.23121/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":"2026-07-28T01:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldg5Y99cyShbswCuP2ajVo2Xh3cy5OJGY07sP6r1u7BeSBNt6RNxcmpxcSyhFiDn9o0/hyKqmbXZB2qoJIGNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:00:20.211553Z"},"content_sha256":"5f2928152e7056a40c918d200e3cae18f9f2312e5c8a835d56b7b3908e6d9c46","schema_version":"1.0","event_id":"sha256:5f2928152e7056a40c918d200e3cae18f9f2312e5c8a835d56b7b3908e6d9c46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ODLFK4HIHXS44PZNNG4H657UQR/bundle.json","state_url":"https://pith.science/pith/ODLFK4HIHXS44PZNNG4H657UQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ODLFK4HIHXS44PZNNG4H657UQR/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":"2026-08-19T00:00:20Z","links":{"resolver":"https://pith.science/pith/ODLFK4HIHXS44PZNNG4H657UQR","bundle":"https://pith.science/pith/ODLFK4HIHXS44PZNNG4H657UQR/bundle.json","state":"https://pith.science/pith/ODLFK4HIHXS44PZNNG4H657UQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ODLFK4HIHXS44PZNNG4H657UQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ODLFK4HIHXS44PZNNG4H657UQR","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":"0235ed4206e8f904949f3b478d2011a87718d332b12c9c49676bbd58b0809ebb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-25T09:41:21Z","title_canon_sha256":"c14c1663d4035b1729a4c4e15dbed4cd92ed16f2b52af127a4ddcdd67fa2bd08"},"schema_version":"1.0","source":{"id":"2607.23121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23121","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23121v1","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23121","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"ODLFK4HIHXS4","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"pith_short_16","alias_value":"ODLFK4HIHXS44PZN","created_at":"2026-07-28T01:22:07Z"},{"alias_kind":"pith_short_8","alias_value":"ODLFK4HI","created_at":"2026-07-28T01:22:07Z"}],"graph_snapshots":[{"event_id":"sha256:5f2928152e7056a40c918d200e3cae18f9f2312e5c8a835d56b7b3908e6d9c46","target":"graph","created_at":"2026-07-28T01:22:07Z","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/2607.23121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories). While Large Language Models (LLMs) capture semantic intent better than traditional embedding models, deploying them at scale introduces prohibitive inference costs and lexical mismatch issues. Through controlled experiments on millions of users, we demonstrate a critical retrieval decomposition: rule-generated queries excel at retargeting on a lexical BM25 index, while LLM-ge","authors_text":"Congfei Zhang, Ge Liu, Hsiang-wei Chao, Jinchao Li, Jingxiao Ma, Meghana Missula, Rachel Liao, Shantanu Aggarwal, Siman Wang, Vincent Zhang, Xiao Bai, XiaoDong Liu, Yajun Wang, Yunzhi Zhou, Yu Zhang, Zhe Liu, Zichu Li","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-25T09:41:21Z","title":"SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23121","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":"sha256:613ff36dcd4c6ab0f17c89daf76595a281c5f86c7268bb2267820288cab6caa7","target":"record","created_at":"2026-07-28T01:22:07Z","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":"0235ed4206e8f904949f3b478d2011a87718d332b12c9c49676bbd58b0809ebb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-25T09:41:21Z","title_canon_sha256":"c14c1663d4035b1729a4c4e15dbed4cd92ed16f2b52af127a4ddcdd67fa2bd08"},"schema_version":"1.0","source":{"id":"2607.23121","kind":"arxiv","version":1}},"canonical_sha256":"70d65570e83de5ce3f2d69b87f77f4846934ae881d83a8b75fcbba1f7649a7d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70d65570e83de5ce3f2d69b87f77f4846934ae881d83a8b75fcbba1f7649a7d6","first_computed_at":"2026-07-28T01:22:07.786541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:07.786541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"InuFWrdBGwD+57xnbUYUPHCMo0oIBuMhrQ4ROMxEq71J00psx0vF83OGTRxvGMZIARq/Yq1510W5bOVne8xdAQ==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:07.787297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:613ff36dcd4c6ab0f17c89daf76595a281c5f86c7268bb2267820288cab6caa7","sha256:5f2928152e7056a40c918d200e3cae18f9f2312e5c8a835d56b7b3908e6d9c46"],"state_sha256":"79a838d7d55427fa7cbd14d1afdfff4f6cd25e77889fbbed17bda77610218a2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GYqbGYg6qGD7ZSA3Z/6kjozZsYhZxAEcfFchsnivQbziD4PJmx/TlrAtQbcTDZkf4OxAwhGKsFwBiaug7oQrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:00:20.217382Z","bundle_sha256":"5b9fa6ec3fbf56b3c730075444959cea95d8bec4ad61e07af5fd982e92e16f45"}}