{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TVUDTKJD2IUK3XGB6FNWINHDKD","short_pith_number":"pith:TVUDTKJD","schema_version":"1.0","canonical_sha256":"9d6839a923d228addcc1f15b6434e350e94273b523c0e064579cf2583384118f","source":{"kind":"arxiv","id":"2208.09846","version":1},"attestation_state":"computed","paper":{"title":"A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiafeng Guo, Ruqing Zhang, Xinyu Ma, Xueqi Cheng, Yixing Fan","submitted_at":"2022-08-21T08:46:18Z","abstract_excerpt":"Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained autoencoder-based language models with a weak decoder can provide high-quality text representations, boosting the effectiveness and few-shot ability of DR models. However, even a weak autoregressive decoder has the bypass effect on the encoder. More importantly, the discriminative ability of learned representations may be limited since each token is treated equally"},"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":"2208.09846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-08-21T08:46:18Z","cross_cats_sorted":[],"title_canon_sha256":"e4ed56f8f45f581b5a81a85d37fedbe75c59109e0a7dcee70e6da9b247bef390","abstract_canon_sha256":"3cc745bb36133c7f96adc028bcb63cbfb4809633e0f47b6707a90357b0ce8644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:50:22.718084Z","signature_b64":"QnKhTzqFQ5/9Gbtw93fhg0A7cbpfUC+jbFSqQbJ1rQd2ARYvkYwjp9PSaq6ALZNJ9ZbVS9zUesqtSMYlySp8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d6839a923d228addcc1f15b6434e350e94273b523c0e064579cf2583384118f","last_reissued_at":"2026-07-05T04:50:22.717706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:50:22.717706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiafeng Guo, Ruqing Zhang, Xinyu Ma, Xueqi Cheng, Yixing Fan","submitted_at":"2022-08-21T08:46:18Z","abstract_excerpt":"Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained autoencoder-based language models with a weak decoder can provide high-quality text representations, boosting the effectiveness and few-shot ability of DR models. However, even a weak autoregressive decoder has the bypass effect on the encoder. More importantly, the discriminative ability of learned representations may be limited since each token is treated equally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09846","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/2208.09846/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":"2208.09846","created_at":"2026-07-05T04:50:22.717749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.09846v1","created_at":"2026-07-05T04:50:22.717749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09846","created_at":"2026-07-05T04:50:22.717749+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVUDTKJD2IUK","created_at":"2026-07-05T04:50:22.717749+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVUDTKJD2IUK3XGB","created_at":"2026-07-05T04:50:22.717749+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVUDTKJD","created_at":"2026-07-05T04:50:22.717749+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/TVUDTKJD2IUK3XGB6FNWINHDKD","json":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD.json","graph_json":"https://pith.science/api/pith-number/TVUDTKJD2IUK3XGB6FNWINHDKD/graph.json","events_json":"https://pith.science/api/pith-number/TVUDTKJD2IUK3XGB6FNWINHDKD/events.json","paper":"https://pith.science/paper/TVUDTKJD"},"agent_actions":{"view_html":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD","download_json":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD.json","view_paper":"https://pith.science/paper/TVUDTKJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.09846&json=true","fetch_graph":"https://pith.science/api/pith-number/TVUDTKJD2IUK3XGB6FNWINHDKD/graph.json","fetch_events":"https://pith.science/api/pith-number/TVUDTKJD2IUK3XGB6FNWINHDKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD/action/storage_attestation","attest_author":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD/action/author_attestation","sign_citation":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD/action/citation_signature","submit_replication":"https://pith.science/pith/TVUDTKJD2IUK3XGB6FNWINHDKD/action/replication_record"}},"created_at":"2026-07-05T04:50:22.717749+00:00","updated_at":"2026-07-05T04:50:22.717749+00:00"}