{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BEEEVGNLGWOSMO2QXBPO3T6PZH","short_pith_number":"pith:BEEEVGNL","canonical_record":{"source":{"id":"2212.08841","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T10:43:25Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"5e70c06c220c4b3cc1ce20a8633bfda3a3c80273604ae18268ead01aca37ca46","abstract_canon_sha256":"f9a02e12bed228a1f8c3d5826347241d4c9ced9e3d06257da49d84ea6070a576"},"schema_version":"1.0"},"canonical_sha256":"09084a99ab359d263b50b85eedcfcfc9d1c8353b40093e46da842348a2d1b7b8","source":{"kind":"arxiv","id":"2212.08841","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BEEEVGNLGWOSMO2QXBPO3T6PZH","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08841","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T10:43:25Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"5e70c06c220c4b3cc1ce20a8633bfda3a3c80273604ae18268ead01aca37ca46","abstract_canon_sha256":"f9a02e12bed228a1f8c3d5826347241d4c9ced9e3d06257da49d84ea6070a576"},"schema_version":"1.0"},"canonical_sha256":"09084a99ab359d263b50b85eedcfcfc9d1c8353b40093e46da842348a2d1b7b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:08.697509Z","signature_b64":"86/ZjnLPZcxO07zu8MUJtx0vVQLsHspKbirpdMCuO7yOmq4bbvAM2rAH9oWD0doglpCEgDLkSZHELAFfZuGYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09084a99ab359d263b50b85eedcfcfc9d1c8353b40093e46da842348a2d1b7b8","last_reissued_at":"2026-07-05T09:28:08.697017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:08.697017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08841","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ZJD1tSHgGa0U/SGkvXIIqtJeZbEFbOkjHrs/lbzOaoYH8wyE02KXHqs4K2Kx/ZKkTMgf+qSi1FRWM16r/x5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:03:38.372731Z"},"content_sha256":"a0b794f954209d6a50728055815875cc1177c234e9788fb9705bd3ea9543779a","schema_version":"1.0","event_id":"sha256:a0b794f954209d6a50728055815875cc1177c234e9788fb9705bd3ea9543779a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BEEEVGNLGWOSMO2QXBPO3T6PZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Divyansh Agarwal, Jianguo Zhang, Lifu Tu, Meghana Bhat, Ning Yu, Rui Meng, Semih Yavuz, Ye Liu, Yingbo Zhou","submitted_at":"2022-12-17T10:43:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08841","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.08841/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fy1b3hglOWFnotIs1gVDtVDiYZEvdZqzNHgpccbs8hlbCwFWOi3I0iV7tGrzkdTzvwjW/fhE8GFfdJd16MXPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:03:38.373254Z"},"content_sha256":"07caccbebc56840ed9eb57eefb0c4775e827b896416e1bcb985e5b4adeba87c3","schema_version":"1.0","event_id":"sha256:07caccbebc56840ed9eb57eefb0c4775e827b896416e1bcb985e5b4adeba87c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BEEEVGNLGWOSMO2QXBPO3T6PZH/bundle.json","state_url":"https://pith.science/pith/BEEEVGNLGWOSMO2QXBPO3T6PZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BEEEVGNLGWOSMO2QXBPO3T6PZH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T22:03:38Z","links":{"resolver":"https://pith.science/pith/BEEEVGNLGWOSMO2QXBPO3T6PZH","bundle":"https://pith.science/pith/BEEEVGNLGWOSMO2QXBPO3T6PZH/bundle.json","state":"https://pith.science/pith/BEEEVGNLGWOSMO2QXBPO3T6PZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BEEEVGNLGWOSMO2QXBPO3T6PZH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fswfA0Y4PanoBb8/+9QmMsPxzUwx/MnavIN7cJOZmqkUgC45HiSh4qN298arkCM2KA0yqJcNXhk7SV76WJi4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:03:38.378662Z","bundle_sha256":"67199f0dafe9e6323474a8aeea2df0efa809ef98833791b68b340558ca7d4952"}}