{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HPUJUJ5LJ7GPWUDTTZ4YLXWXC3","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":"bbfb41489fa2e6a2e581f2be1407e0c92409410bad8b07fbe88861e91f4ed45d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-07-06T10:51:33Z","title_canon_sha256":"7cb08ff0427ea6fd139d7fa6342ef6ad90a83d5865a63a76d73b3d56701d85f0"},"schema_version":"1.0","source":{"id":"2207.02578","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.02578","created_at":"2026-07-05T06:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2207.02578v2","created_at":"2026-07-05T06:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02578","created_at":"2026-07-05T06:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"HPUJUJ5LJ7GP","created_at":"2026-07-05T06:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"HPUJUJ5LJ7GPWUDT","created_at":"2026-07-05T06:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"HPUJUJ5L","created_at":"2026-07-05T06:09:31Z"}],"graph_snapshots":[{"event_id":"sha256:78287a562694489bbfb90661477bce62a2f321362f9cdd7f7f20b9dd376b1b99","target":"graph","created_at":"2026-07-05T06:09:31Z","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/2207.02578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose SimLM (Similarity matching with Language Model pre-training), a simple yet effective pre-training method for dense passage retrieval. It employs a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training. We use a replaced language modeling objective, which is inspired by ELECTRA, to improve the sample efficiency and reduce the mismatch of the input distribution between pre-training and fine-tuning. SimLM only requires access to unlabeled corpus, and is more broadly applicable when there ar","authors_text":"Binxing Jiao, Daxin Jiang, Furu Wei, Liang Wang, Linjun Yang, Nan Yang, Rangan Majumder, Xiaolong Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-07-06T10:51:33Z","title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02578","kind":"arxiv","version":2},"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:ce5607c8688400600a35a9d2a7a30bb80dceb65945c1318ef0fb3ffb6fca4e69","target":"record","created_at":"2026-07-05T06:09:31Z","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":"bbfb41489fa2e6a2e581f2be1407e0c92409410bad8b07fbe88861e91f4ed45d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-07-06T10:51:33Z","title_canon_sha256":"7cb08ff0427ea6fd139d7fa6342ef6ad90a83d5865a63a76d73b3d56701d85f0"},"schema_version":"1.0","source":{"id":"2207.02578","kind":"arxiv","version":2}},"canonical_sha256":"3be89a27ab4fccfb50739e7985ded716e5744f586b1941e60e05230fb29aad26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3be89a27ab4fccfb50739e7985ded716e5744f586b1941e60e05230fb29aad26","first_computed_at":"2026-07-05T06:09:31.389340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:31.389340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TMEkJm7BfKoqRV8kHuFdDO6RjpdzwJC1cmytM5JIPrUo+HqApD2Utul7yP3GXSDTxhNrlH2YWk+zH5/smGEmCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:31.389760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.02578","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce5607c8688400600a35a9d2a7a30bb80dceb65945c1318ef0fb3ffb6fca4e69","sha256:78287a562694489bbfb90661477bce62a2f321362f9cdd7f7f20b9dd376b1b99"],"state_sha256":"f0f3a0c56683a2db15bdef1df145bf215c9922f99882e58cb1a020bb6c1f47c8"}