{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4YY5ZULTM44CLZABASMEJGDI7W","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":"94ed386332dfb987abe69306f6642ab56141481d029ab8b5e8ef6d2a41b8147a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-08-12T05:20:27Z","title_canon_sha256":"348d7b8080a8e7fc54323c1041c844f0d2486b54f9279a89004c1dde19e0c8e5"},"schema_version":"1.0","source":{"id":"2108.05540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05540","created_at":"2026-07-05T03:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05540v1","created_at":"2026-07-05T03:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05540","created_at":"2026-07-05T03:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"4YY5ZULTM44C","created_at":"2026-07-05T03:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"4YY5ZULTM44CLZAB","created_at":"2026-07-05T03:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"4YY5ZULT","created_at":"2026-07-05T03:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:b6f6c8b058769e541d847bcf41a2ea0cbf73451563826adb02cc3a87e30963fc","target":"graph","created_at":"2026-07-05T03:05:15Z","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/2108.05540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full potential. In this paper, we identify and address two underlying problems of dense retrievers: i)~fragility to training data noise and ii)~requiring large batches to robustly learn the embedding space. We use the recently proposed Condenser pre-training architecture, which learns to condense information into the dense vector through LM pre-training. On top of i","authors_text":"Jamie Callan, Luyu Gao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-08-12T05:20:27Z","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05540","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":"sha256:51d730f8afda74ad20911580257fcb9f7a5d9ce62f10054ae22ec55730264b62","target":"record","created_at":"2026-07-05T03:05:15Z","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":"94ed386332dfb987abe69306f6642ab56141481d029ab8b5e8ef6d2a41b8147a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-08-12T05:20:27Z","title_canon_sha256":"348d7b8080a8e7fc54323c1041c844f0d2486b54f9279a89004c1dde19e0c8e5"},"schema_version":"1.0","source":{"id":"2108.05540","kind":"arxiv","version":1}},"canonical_sha256":"e631dcd173673825e4010498449868fdaf4a49cb218d5a23d4c4810a2bacd0a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e631dcd173673825e4010498449868fdaf4a49cb218d5a23d4c4810a2bacd0a4","first_computed_at":"2026-07-05T03:05:15.342992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:15.342992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0O0UvGQrvNvaaNRCryDTFZ7nf2w7hAxFiYMw9+zuuIfz1SMd12yFP8u3apzem3k/ZTCYbXRm4BghGZfEjG9qBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:15.343410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51d730f8afda74ad20911580257fcb9f7a5d9ce62f10054ae22ec55730264b62","sha256:b6f6c8b058769e541d847bcf41a2ea0cbf73451563826adb02cc3a87e30963fc"],"state_sha256":"10dac7e30fb830d94aa0b45861856f127e3bdaf15b7850247d51d2033cd82a8b"}