{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NJVM4EMZVBI7YDV6KWFEVQK5X6","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":"65cd1ff6c7c31a4cbdcd0a546b52ca8aed19e6ee44088ae40657471ce1a86656","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T08:08:17Z","title_canon_sha256":"57d0e2fc16db409ce1b1f71613447b3f331e2ef40aa64aeb1a6ac8f1550a024e"},"schema_version":"1.0","source":{"id":"2102.09206","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09206","created_at":"2026-07-05T03:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09206v3","created_at":"2026-07-05T03:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09206","created_at":"2026-07-05T03:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"NJVM4EMZVBI7","created_at":"2026-07-05T03:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"NJVM4EMZVBI7YDV6","created_at":"2026-07-05T03:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"NJVM4EMZ","created_at":"2026-07-05T03:14:53Z"}],"graph_snapshots":[{"event_id":"sha256:181eb1f8e3c94ca8044afb975b0bb9da42f7adf7013c18eecadd121d0136c969","target":"graph","created_at":"2026-07-05T03:14:53Z","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/2102.09206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality embedding that can reconstruct the input texts. However, in this paper, we provide theoretical analyses and show empirically that an autoencoder language model with a low reconstruction loss may not provide good sequence representations because the decoder may take shortcuts by exploiting language patterns. To address this, we propose a new self-learning method ","authors_text":"Arnold Overwijk, Chenyan Xiong, Di He, Guolin Ke, Paul Bennett, Shuqi Lu, Tieyan Liu, Waleed Malik, Zhicheng Dou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T08:08:17Z","title":"Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09206","kind":"arxiv","version":3},"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":"sha256:5e0b069d42bc96730afa7e46aea302e3aa21d2dede5a19d24f2688ca951f9948","target":"record","created_at":"2026-07-05T03:14:53Z","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":"65cd1ff6c7c31a4cbdcd0a546b52ca8aed19e6ee44088ae40657471ce1a86656","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T08:08:17Z","title_canon_sha256":"57d0e2fc16db409ce1b1f71613447b3f331e2ef40aa64aeb1a6ac8f1550a024e"},"schema_version":"1.0","source":{"id":"2102.09206","kind":"arxiv","version":3}},"canonical_sha256":"6a6ace1199a851fc0ebe558a4ac15dbf939456a145e092a7c7edeac05937b3f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a6ace1199a851fc0ebe558a4ac15dbf939456a145e092a7c7edeac05937b3f9","first_computed_at":"2026-07-05T03:14:53.858124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:53.858124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0o4FBnErQ1IphbaKnusPrm6s/8LGDNdnsO9tqmmFLpW4C0c1kMNVobu+NkKtPjo3gDFQ3bTK2PmeHWn0n6K+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:53.858663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.09206","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e0b069d42bc96730afa7e46aea302e3aa21d2dede5a19d24f2688ca951f9948","sha256:181eb1f8e3c94ca8044afb975b0bb9da42f7adf7013c18eecadd121d0136c969"],"state_sha256":"3ca7fc2909fe193a9c481ee54f91c27f6913dfeaec1ad80522666b6d3d61754a"}