{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NAHUQB3B3TTWMIJB5N66EPLYF3","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":"f92094466b49eeedffc5828787d0f67e37a3e538ad569bfd36287014f37416f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-20T07:07:56Z","title_canon_sha256":"eecd2c252736b575faff1a1b7154e32ef87e67a5f96ada88eba3bcb15f1a30b1"},"schema_version":"1.0","source":{"id":"2104.09791","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09791","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09791v4","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09791","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"NAHUQB3B3TTW","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"NAHUQB3B3TTWMIJB","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"NAHUQB3B","created_at":"2026-07-05T04:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:ac932d72d58a22b340f49b8724cc9d0c532dd98ceca061cb00c2060ea2931fb9","target":"graph","created_at":"2026-07-05T04:18:14Z","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/2104.09791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training and fine-tuning have achieved remarkable success in many downstream natural language processing (NLP) tasks. Recently, pre-training methods tailored for information retrieval (IR) have also been explored, and the latest success is the PROP method which has reached new SOTA on a variety of ad-hoc retrieval benchmarks. The basic idea of PROP is to construct the \\textit{representative words prediction} (ROP) task for pre-training inspired by the query likelihood model. Despite its exciting performance, the effectiveness of PROP might be bounded by the classical unigram language model","authors_text":"Jiafeng Guo, Ruqing Zhang, Xinyu Ma, Xueqi Cheng, Yingyan Li, Yixing Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-20T07:07:56Z","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09791","kind":"arxiv","version":4},"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:f6cbda916e55f02f469e774ebf9b04ca50b3e0d991eaaf5166733416bd3e22a9","target":"record","created_at":"2026-07-05T04:18:14Z","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":"f92094466b49eeedffc5828787d0f67e37a3e538ad569bfd36287014f37416f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-20T07:07:56Z","title_canon_sha256":"eecd2c252736b575faff1a1b7154e32ef87e67a5f96ada88eba3bcb15f1a30b1"},"schema_version":"1.0","source":{"id":"2104.09791","kind":"arxiv","version":4}},"canonical_sha256":"680f480761dce7662121eb7de23d782ed79efb553521480fd7dd6041d6f1627d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"680f480761dce7662121eb7de23d782ed79efb553521480fd7dd6041d6f1627d","first_computed_at":"2026-07-05T04:18:14.537276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:18:14.537276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"noyAS5fqv9L2FPTnkJblwI0FoUI99/l3925bwqiVtQkMYzWV+OkoIkyps5mq+IC4CBDMR9UieA005PDWk6WkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:18:14.537745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09791","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6cbda916e55f02f469e774ebf9b04ca50b3e0d991eaaf5166733416bd3e22a9","sha256:ac932d72d58a22b340f49b8724cc9d0c532dd98ceca061cb00c2060ea2931fb9"],"state_sha256":"bac783b763bf2f2c3037feee2222c54aa9553d2b39285336fc9fbe67ca4486a9"}