{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BEEEVGNLGWOSMO2QXBPO3T6PZH","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":"f9a02e12bed228a1f8c3d5826347241d4c9ced9e3d06257da49d84ea6070a576","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T10:43:25Z","title_canon_sha256":"5e70c06c220c4b3cc1ce20a8633bfda3a3c80273604ae18268ead01aca37ca46"},"schema_version":"1.0","source":{"id":"2212.08841","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08841","created_at":"2026-07-05T09:28:08Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08841v4","created_at":"2026-07-05T09:28:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08841","created_at":"2026-07-05T09:28:08Z"},{"alias_kind":"pith_short_12","alias_value":"BEEEVGNLGWOS","created_at":"2026-07-05T09:28:08Z"},{"alias_kind":"pith_short_16","alias_value":"BEEEVGNLGWOSMO2Q","created_at":"2026-07-05T09:28:08Z"},{"alias_kind":"pith_short_8","alias_value":"BEEEVGNL","created_at":"2026-07-05T09:28:08Z"}],"graph_snapshots":[{"event_id":"sha256:07caccbebc56840ed9eb57eefb0c4775e827b896416e1bcb985e5b4adeba87c3","target":"graph","created_at":"2026-07-05T09:28:08Z","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/2212.08841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-annotated supervision. In this study, we aim to develop unsupervised methods for improving dense retrieval models. We propose two approaches that enable annotation-free and scalable training by creating pseudo querydocument pairs: query extraction and transferred query generation. The query extraction method involves selecting salient spans from the original document to generate pseudo queries. On the other hand, the tra","authors_text":"Divyansh Agarwal, Jianguo Zhang, Lifu Tu, Meghana Bhat, Ning Yu, Rui Meng, Semih Yavuz, Ye Liu, Yingbo Zhou","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T10:43:25Z","title":"AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08841","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:a0b794f954209d6a50728055815875cc1177c234e9788fb9705bd3ea9543779a","target":"record","created_at":"2026-07-05T09:28:08Z","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":"f9a02e12bed228a1f8c3d5826347241d4c9ced9e3d06257da49d84ea6070a576","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T10:43:25Z","title_canon_sha256":"5e70c06c220c4b3cc1ce20a8633bfda3a3c80273604ae18268ead01aca37ca46"},"schema_version":"1.0","source":{"id":"2212.08841","kind":"arxiv","version":4}},"canonical_sha256":"09084a99ab359d263b50b85eedcfcfc9d1c8353b40093e46da842348a2d1b7b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09084a99ab359d263b50b85eedcfcfc9d1c8353b40093e46da842348a2d1b7b8","first_computed_at":"2026-07-05T09:28:08.697017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:08.697017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"86/ZjnLPZcxO07zu8MUJtx0vVQLsHspKbirpdMCuO7yOmq4bbvAM2rAH9oWD0doglpCEgDLkSZHELAFfZuGYCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:08.697509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08841","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0b794f954209d6a50728055815875cc1177c234e9788fb9705bd3ea9543779a","sha256:07caccbebc56840ed9eb57eefb0c4775e827b896416e1bcb985e5b4adeba87c3"],"state_sha256":"0e308cda71bb3e918d0314b1f00eb00ec31a973a3d089470c88e71d5d00c9272"}