{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HUOWHBPEHUIWSEQZNSVSH6QUAZ","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":"eb42b8d1e8d8d9eb5e28cb8d4e603c18ea1ce9a55ea3a7f00ad722a782f67c28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-04-22T11:22:29Z","title_canon_sha256":"2ca3ebb5028d34d52de96942ac7958eca903799eb57b5d74bfff916058290fb3"},"schema_version":"1.0","source":{"id":"2204.10641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.10641","created_at":"2026-07-05T04:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2204.10641v1","created_at":"2026-07-05T04:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10641","created_at":"2026-07-05T04:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"HUOWHBPEHUIW","created_at":"2026-07-05T04:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"HUOWHBPEHUIWSEQZ","created_at":"2026-07-05T04:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"HUOWHBPE","created_at":"2026-07-05T04:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:92c242e9dca9f019b0128638523aca689d07bf81dc13fe275da0efb0e6ad1c4a","target":"graph","created_at":"2026-07-05T04:16:59Z","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/2204.10641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense retrieval has shown promising results in many information retrieval (IR) related tasks, whose foundation is high-quality text representation learning for effective search. Some recent studies have shown that autoencoder-based language models are able to boost the dense retrieval performance using a weak decoder. However, we argue that 1) it is not discriminative to decode all the input texts and, 2) even a weak decoder has the bypass effect on the encoder. Therefore, in this work, we introduce a novel contrastive span prediction task to pre-train the encoder alone, but still retain the b","authors_text":"Jiafeng Guo, Ruqing Zhang, Xinyu Ma, Xueqi Cheng, Yixing Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-04-22T11:22:29Z","title":"Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10641","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":"sha256:00e5e295b08aba956fb590cea921f789b4b1a788be9684217241daf7c93c38a5","target":"record","created_at":"2026-07-05T04:16:59Z","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":"eb42b8d1e8d8d9eb5e28cb8d4e603c18ea1ce9a55ea3a7f00ad722a782f67c28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-04-22T11:22:29Z","title_canon_sha256":"2ca3ebb5028d34d52de96942ac7958eca903799eb57b5d74bfff916058290fb3"},"schema_version":"1.0","source":{"id":"2204.10641","kind":"arxiv","version":1}},"canonical_sha256":"3d1d6385e43d116912196cab23fa14064241f5c1fbc2f01fcbaa3eba1a359b22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d1d6385e43d116912196cab23fa14064241f5c1fbc2f01fcbaa3eba1a359b22","first_computed_at":"2026-07-05T04:16:59.391309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:59.391309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6bA8DxjYdvn7t1Jk22JLmtWNCEQD4XkLu8wzz5xxYLipKOGMrR/q7rdTX1b867zGke92DUtJxwFNvuCX/FCdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:59.391757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.10641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00e5e295b08aba956fb590cea921f789b4b1a788be9684217241daf7c93c38a5","sha256:92c242e9dca9f019b0128638523aca689d07bf81dc13fe275da0efb0e6ad1c4a"],"state_sha256":"5d6bc37819bba0ec2ae2570468a892f03caecda8296dcf4cada6eec4e60607ab"}