{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NMK3NUF7ESPGWLTACYUPOAHUTH","short_pith_number":"pith:NMK3NUF7","schema_version":"1.0","canonical_sha256":"6b15b6d0bf249e6b2e601628f700f499f209d91d11698255aaba959a95afd4c6","source":{"kind":"arxiv","id":"2212.09114","version":2},"attestation_state":"computed","paper":{"title":"CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A-Long Jin, Anlei Dong, Hang Zhang, Jian Jiao, Nan Duan, Siu Ming Yiu, Xingwei He, Yeyun Gong","submitted_at":"2022-12-18T15:57:46Z","abstract_excerpt":"The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and document. To alleviate this, recent research has focused on obtaining query-informed document representations. During training, it expands the document with a real query, but during inference, it replaces the real query with a generated one. This inconsistency between training and inference causes the dense retrieval model to prioritize query information while di"},"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":"2212.09114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-18T15:57:46Z","cross_cats_sorted":[],"title_canon_sha256":"8f496d68a34f97c915ab1375c73259aaf339851cacbb7fe490394f7af1e64fe9","abstract_canon_sha256":"4b7adb440572238ed70eed4f29f4b298cfeee7970c9181ba3125428938a5f417"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:21.960918Z","signature_b64":"mBTfSTHwuAHJJOT59yW02UkP0Mfb8r64qHk/T9mP09qbLxXVo+KgusNd3AriB0U0syWVJcHMPjSoQ83ZG/o9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b15b6d0bf249e6b2e601628f700f499f209d91d11698255aaba959a95afd4c6","last_reissued_at":"2026-07-05T07:06:21.960322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:21.960322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A-Long Jin, Anlei Dong, Hang Zhang, Jian Jiao, Nan Duan, Siu Ming Yiu, Xingwei He, Yeyun Gong","submitted_at":"2022-12-18T15:57:46Z","abstract_excerpt":"The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and document. To alleviate this, recent research has focused on obtaining query-informed document representations. During training, it expands the document with a real query, but during inference, it replaces the real query with a generated one. This inconsistency between training and inference causes the dense retrieval model to prioritize query information while di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09114","kind":"arxiv","version":2},"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/2212.09114/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":"2212.09114","created_at":"2026-07-05T07:06:21.960378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09114v2","created_at":"2026-07-05T07:06:21.960378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09114","created_at":"2026-07-05T07:06:21.960378+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMK3NUF7ESPG","created_at":"2026-07-05T07:06:21.960378+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMK3NUF7ESPGWLTA","created_at":"2026-07-05T07:06:21.960378+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMK3NUF7","created_at":"2026-07-05T07:06:21.960378+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/NMK3NUF7ESPGWLTACYUPOAHUTH","json":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH.json","graph_json":"https://pith.science/api/pith-number/NMK3NUF7ESPGWLTACYUPOAHUTH/graph.json","events_json":"https://pith.science/api/pith-number/NMK3NUF7ESPGWLTACYUPOAHUTH/events.json","paper":"https://pith.science/paper/NMK3NUF7"},"agent_actions":{"view_html":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH","download_json":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH.json","view_paper":"https://pith.science/paper/NMK3NUF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09114&json=true","fetch_graph":"https://pith.science/api/pith-number/NMK3NUF7ESPGWLTACYUPOAHUTH/graph.json","fetch_events":"https://pith.science/api/pith-number/NMK3NUF7ESPGWLTACYUPOAHUTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH/action/storage_attestation","attest_author":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH/action/author_attestation","sign_citation":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH/action/citation_signature","submit_replication":"https://pith.science/pith/NMK3NUF7ESPGWLTACYUPOAHUTH/action/replication_record"}},"created_at":"2026-07-05T07:06:21.960378+00:00","updated_at":"2026-07-05T07:06:21.960378+00:00"}