{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QMQPCNG4GTDLFP6MB76HBJCMOA","short_pith_number":"pith:QMQPCNG4","canonical_record":{"source":{"id":"2304.08138","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T10:42:30Z","cross_cats_sorted":[],"title_canon_sha256":"fddbe6d8ac34ddb5b90dfe0fe50d000993490a08bed2921fc34e78e06effffa8","abstract_canon_sha256":"43e6bb25bc6c3aada807c2e3d706aed5fa96095df244d27d782740cd839707a4"},"schema_version":"1.0"},"canonical_sha256":"8320f134dc34c6b2bfcc0ffc70a44c70129271a980cd5ea6508e58ac0f4d956a","source":{"kind":"arxiv","id":"2304.08138","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08138","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08138v2","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08138","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"QMQPCNG4GTDL","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"QMQPCNG4GTDLFP6M","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"QMQPCNG4","created_at":"2026-07-05T07:16:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QMQPCNG4GTDLFP6MB76HBJCMOA","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08138","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T10:42:30Z","cross_cats_sorted":[],"title_canon_sha256":"fddbe6d8ac34ddb5b90dfe0fe50d000993490a08bed2921fc34e78e06effffa8","abstract_canon_sha256":"43e6bb25bc6c3aada807c2e3d706aed5fa96095df244d27d782740cd839707a4"},"schema_version":"1.0"},"canonical_sha256":"8320f134dc34c6b2bfcc0ffc70a44c70129271a980cd5ea6508e58ac0f4d956a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:40.435119Z","signature_b64":"ZohXkMwgHSSVE3GZE8/7Uls9cB7MShY5C+WMRaQlEVLHhkOiI4Yb4dj1sG+6yR7eVtKgXW7rClF0tAWqXLdSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8320f134dc34c6b2bfcc0ffc70a44c70129271a980cd5ea6508e58ac0f4d956a","last_reissued_at":"2026-07-05T07:16:40.434590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:40.434590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08138","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afhVR6RPPmFqqRl3mBon4sg7xmtsjusiE9bauauP0AoZZ34N+N9B+BHpWRapz+snP3I6tRBvPp4mCiYA0E6GBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:53:39.641102Z"},"content_sha256":"1e8097615439d4c72006624f262999ba21117f025d5460bc3fd0be6677c45c45","schema_version":"1.0","event_id":"sha256:1e8097615439d4c72006624f262999ba21117f025d5460bc3fd0be6677c45c45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QMQPCNG4GTDLFP6MB76HBJCMOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Guido Zuccon, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Shengyao Zhuang","submitted_at":"2023-04-17T10:42:30Z","abstract_excerpt":"Current dense retrievers (DRs) are limited in their ability to effectively process misspelled queries, which constitute a significant portion of query traffic in commercial search engines. The main issue is that the pre-trained language model-based encoders used by DRs are typically trained and fine-tuned using clean, well-curated text data. Misspelled queries are typically not found in the data used for training these models, and thus misspelled queries observed at inference time are out-of-distribution compared to the data used for training and fine-tuning. Previous efforts to address this i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08138","kind":"arxiv","version":2},"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/2304.08138/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":"2026-07-05T07:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DbHMbnnuvmP4QYYYpLFEiLLnhjp+aNDmfMsfav7lRxkVaxvTgsTxT+Gtk+qZZCfiygqqHjYSWY5e0Uy6NUUlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:53:39.641490Z"},"content_sha256":"d450631ba798184ed74961ae44e100a170df224148dcbbff79cfa856b704e2e4","schema_version":"1.0","event_id":"sha256:d450631ba798184ed74961ae44e100a170df224148dcbbff79cfa856b704e2e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/bundle.json","state_url":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/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":"2026-07-06T16:53:39Z","links":{"resolver":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA","bundle":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/bundle.json","state":"https://pith.science/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMQPCNG4GTDLFP6MB76HBJCMOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QMQPCNG4GTDLFP6MB76HBJCMOA","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":"43e6bb25bc6c3aada807c2e3d706aed5fa96095df244d27d782740cd839707a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T10:42:30Z","title_canon_sha256":"fddbe6d8ac34ddb5b90dfe0fe50d000993490a08bed2921fc34e78e06effffa8"},"schema_version":"1.0","source":{"id":"2304.08138","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08138","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08138v2","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08138","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"QMQPCNG4GTDL","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"QMQPCNG4GTDLFP6M","created_at":"2026-07-05T07:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"QMQPCNG4","created_at":"2026-07-05T07:16:40Z"}],"graph_snapshots":[{"event_id":"sha256:d450631ba798184ed74961ae44e100a170df224148dcbbff79cfa856b704e2e4","target":"graph","created_at":"2026-07-05T07:16:40Z","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/2304.08138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current dense retrievers (DRs) are limited in their ability to effectively process misspelled queries, which constitute a significant portion of query traffic in commercial search engines. The main issue is that the pre-trained language model-based encoders used by DRs are typically trained and fine-tuned using clean, well-curated text data. Misspelled queries are typically not found in the data used for training these models, and thus misspelled queries observed at inference time are out-of-distribution compared to the data used for training and fine-tuning. Previous efforts to address this i","authors_text":"Daxin Jiang, Guido Zuccon, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Shengyao Zhuang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T10:42:30Z","title":"Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08138","kind":"arxiv","version":2},"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":"sha256:1e8097615439d4c72006624f262999ba21117f025d5460bc3fd0be6677c45c45","target":"record","created_at":"2026-07-05T07:16:40Z","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":"43e6bb25bc6c3aada807c2e3d706aed5fa96095df244d27d782740cd839707a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T10:42:30Z","title_canon_sha256":"fddbe6d8ac34ddb5b90dfe0fe50d000993490a08bed2921fc34e78e06effffa8"},"schema_version":"1.0","source":{"id":"2304.08138","kind":"arxiv","version":2}},"canonical_sha256":"8320f134dc34c6b2bfcc0ffc70a44c70129271a980cd5ea6508e58ac0f4d956a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8320f134dc34c6b2bfcc0ffc70a44c70129271a980cd5ea6508e58ac0f4d956a","first_computed_at":"2026-07-05T07:16:40.434590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:40.434590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZohXkMwgHSSVE3GZE8/7Uls9cB7MShY5C+WMRaQlEVLHhkOiI4Yb4dj1sG+6yR7eVtKgXW7rClF0tAWqXLdSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:40.435119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08138","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e8097615439d4c72006624f262999ba21117f025d5460bc3fd0be6677c45c45","sha256:d450631ba798184ed74961ae44e100a170df224148dcbbff79cfa856b704e2e4"],"state_sha256":"fa5af2ce2081d686f91a28a919d80e812161b3fa96c7030f0c9431cdcf9f83fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AbmpnqThvIgsu3CGstjJLVxzQ2UQjs7vhmwDIOoHxNRjgsJIG62pdrTBe+RiXn+icCyGbUzes9GlDl41mrkYAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:53:39.643509Z","bundle_sha256":"456e3e85e723e20e089fa54a1ad39700a78a6383afab08042defa8faea59bd6e"}}