{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MGOAFXLQLSGTVHURZLF7LHPNXT","short_pith_number":"pith:MGOAFXLQ","schema_version":"1.0","canonical_sha256":"619c02dd705c8d3a9e91cacbf59dedbcfcdc892f15bb0a68a01315f552c575be","source":{"kind":"arxiv","id":"2304.10195","version":1},"attestation_state":"computed","paper":{"title":"CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guangyuan Ma, Peng Wang, Songlin Hu, Xing Wu","submitted_at":"2023-04-20T10:12:09Z","abstract_excerpt":"Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for passage retrieval. Siamese or fully separated dual-encoders are often adopted as basic retrieval architecture in the pre-training and fine-tuning stages for encoding queries and passages into their latent embedding spaces. However, simply sharing or separating the parameters of the dual-encoder results in an imbalanced discrimination of the embedding spaces. In "},"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":"2304.10195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-20T10:12:09Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"0e71976a4cf655df8015b38b67cdf50b99325a19ea12021b2bb6ce59c449e0e2","abstract_canon_sha256":"79d124d5a6cd359d985025587d60609c9cf8a683c0d8b91750adbcca88089b81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:55.073554Z","signature_b64":"K+ghQAiVup3zUg6xyRE7P8ACtyWCv8f5whVqVxnK6uReWbs/bERGIULDr5tQYY9DetQ7wtrzf1fnXGGOcghUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"619c02dd705c8d3a9e91cacbf59dedbcfcdc892f15bb0a68a01315f552c575be","last_reissued_at":"2026-07-05T06:02:55.073123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:55.073123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guangyuan Ma, Peng Wang, Songlin Hu, Xing Wu","submitted_at":"2023-04-20T10:12:09Z","abstract_excerpt":"Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for passage retrieval. Siamese or fully separated dual-encoders are often adopted as basic retrieval architecture in the pre-training and fine-tuning stages for encoding queries and passages into their latent embedding spaces. However, simply sharing or separating the parameters of the dual-encoder results in an imbalanced discrimination of the embedding spaces. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10195","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/2304.10195/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":"2304.10195","created_at":"2026-07-05T06:02:55.073176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10195v1","created_at":"2026-07-05T06:02:55.073176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10195","created_at":"2026-07-05T06:02:55.073176+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGOAFXLQLSGT","created_at":"2026-07-05T06:02:55.073176+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGOAFXLQLSGTVHUR","created_at":"2026-07-05T06:02:55.073176+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGOAFXLQ","created_at":"2026-07-05T06:02:55.073176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20970","citing_title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT","json":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT.json","graph_json":"https://pith.science/api/pith-number/MGOAFXLQLSGTVHURZLF7LHPNXT/graph.json","events_json":"https://pith.science/api/pith-number/MGOAFXLQLSGTVHURZLF7LHPNXT/events.json","paper":"https://pith.science/paper/MGOAFXLQ"},"agent_actions":{"view_html":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT","download_json":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT.json","view_paper":"https://pith.science/paper/MGOAFXLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10195&json=true","fetch_graph":"https://pith.science/api/pith-number/MGOAFXLQLSGTVHURZLF7LHPNXT/graph.json","fetch_events":"https://pith.science/api/pith-number/MGOAFXLQLSGTVHURZLF7LHPNXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT/action/storage_attestation","attest_author":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT/action/author_attestation","sign_citation":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT/action/citation_signature","submit_replication":"https://pith.science/pith/MGOAFXLQLSGTVHURZLF7LHPNXT/action/replication_record"}},"created_at":"2026-07-05T06:02:55.073176+00:00","updated_at":"2026-07-05T06:02:55.073176+00:00"}