{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SIERT4PKF7NB6OMLKPAF2QOMYQ","short_pith_number":"pith:SIERT4PK","canonical_record":{"source":{"id":"2204.00716","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2022-04-01T23:02:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"795f51d052e63154eef18b334d13cc0cbc54b075eac5a4cfc1634dc9379e4716","abstract_canon_sha256":"c5225f20e233047573cec6d03b2b706423af92d6965acffd1abe592cc7e76769"},"schema_version":"1.0"},"canonical_sha256":"920919f1ea2fda1f398b53c05d41ccc43a4a83199f7150750a12900cdec94254","source":{"kind":"arxiv","id":"2204.00716","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00716","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00716v2","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00716","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"SIERT4PKF7NB","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"SIERT4PKF7NB6OML","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"SIERT4PK","created_at":"2026-07-05T04:17:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SIERT4PKF7NB6OMLKPAF2QOMYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2204.00716","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2022-04-01T23:02:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"795f51d052e63154eef18b334d13cc0cbc54b075eac5a4cfc1634dc9379e4716","abstract_canon_sha256":"c5225f20e233047573cec6d03b2b706423af92d6965acffd1abe592cc7e76769"},"schema_version":"1.0"},"canonical_sha256":"920919f1ea2fda1f398b53c05d41ccc43a4a83199f7150750a12900cdec94254","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:39.930566Z","signature_b64":"N17Tx7CLTQiO0MRGv+AG8R1Vo7raVWgOfQdGZTtIcpET8RZyg8jxFQetR/sqj6eTYs/kYV7hW0BXokKJypWsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"920919f1ea2fda1f398b53c05d41ccc43a4a83199f7150750a12900cdec94254","last_reissued_at":"2026-07-05T04:17:39.930078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:39.930078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.00716","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":"2026-07-05T04:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDvSKhE3sM00Jz+YYf+K5Bg/BYbAv5ub+t20KXCaH+ZcKA3IOzY0msFGTz7dk0Dg0ekVhCt7q4qLcTOfDK8DDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:28:18.596288Z"},"content_sha256":"bcb9747aa89626f910ce87974f22a75c626877ca3f48445fc33d23fd67f013a8","schema_version":"1.0","event_id":"sha256:bcb9747aa89626f910ce87974f22a75c626877ca3f48445fc33d23fd67f013a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SIERT4PKF7NB6OMLKPAF2QOMYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guido Zuccon, Shengyao Zhuang","submitted_at":"2022-04-01T23:02:50Z","abstract_excerpt":"Current dense retrievers are not robust to out-of-domain and outlier queries, i.e. their effectiveness on these queries is much poorer than what one would expect. In this paper, we consider a specific instance of such queries: queries that contain typos. We show that a small character level perturbation in queries (as caused by typos) highly impacts the effectiveness of dense retrievers. We then demonstrate that the root cause of this resides in the input tokenization strategy employed by BERT. In BERT, tokenization is performed using the BERT's WordPiece tokenizer and we show that a token wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00716","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/2204.00716/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":"2026-07-05T04:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GvhkBciRj4/N7U5LeX0jkzN8QxflG3g71XmxRZVnvVnOmr5p6vLPtZwYtqESMaDddUJ+JMVCD8HRML76NzuBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:28:18.596683Z"},"content_sha256":"ccfff8b65280e04e949a3cd1e0c27639a90368125bbba6861c80f0e70fdd66f7","schema_version":"1.0","event_id":"sha256:ccfff8b65280e04e949a3cd1e0c27639a90368125bbba6861c80f0e70fdd66f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SIERT4PKF7NB6OMLKPAF2QOMYQ/bundle.json","state_url":"https://pith.science/pith/SIERT4PKF7NB6OMLKPAF2QOMYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SIERT4PKF7NB6OMLKPAF2QOMYQ/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":"2026-07-06T12:28:18Z","links":{"resolver":"https://pith.science/pith/SIERT4PKF7NB6OMLKPAF2QOMYQ","bundle":"https://pith.science/pith/SIERT4PKF7NB6OMLKPAF2QOMYQ/bundle.json","state":"https://pith.science/pith/SIERT4PKF7NB6OMLKPAF2QOMYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SIERT4PKF7NB6OMLKPAF2QOMYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SIERT4PKF7NB6OMLKPAF2QOMYQ","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":"c5225f20e233047573cec6d03b2b706423af92d6965acffd1abe592cc7e76769","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2022-04-01T23:02:50Z","title_canon_sha256":"795f51d052e63154eef18b334d13cc0cbc54b075eac5a4cfc1634dc9379e4716"},"schema_version":"1.0","source":{"id":"2204.00716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00716","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00716v2","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00716","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"SIERT4PKF7NB","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"SIERT4PKF7NB6OML","created_at":"2026-07-05T04:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"SIERT4PK","created_at":"2026-07-05T04:17:39Z"}],"graph_snapshots":[{"event_id":"sha256:ccfff8b65280e04e949a3cd1e0c27639a90368125bbba6861c80f0e70fdd66f7","target":"graph","created_at":"2026-07-05T04:17:39Z","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/2204.00716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current dense retrievers are not robust to out-of-domain and outlier queries, i.e. their effectiveness on these queries is much poorer than what one would expect. In this paper, we consider a specific instance of such queries: queries that contain typos. We show that a small character level perturbation in queries (as caused by typos) highly impacts the effectiveness of dense retrievers. We then demonstrate that the root cause of this resides in the input tokenization strategy employed by BERT. In BERT, tokenization is performed using the BERT's WordPiece tokenizer and we show that a token wit","authors_text":"Guido Zuccon, Shengyao Zhuang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2022-04-01T23:02:50Z","title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00716","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:bcb9747aa89626f910ce87974f22a75c626877ca3f48445fc33d23fd67f013a8","target":"record","created_at":"2026-07-05T04:17:39Z","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":"c5225f20e233047573cec6d03b2b706423af92d6965acffd1abe592cc7e76769","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2022-04-01T23:02:50Z","title_canon_sha256":"795f51d052e63154eef18b334d13cc0cbc54b075eac5a4cfc1634dc9379e4716"},"schema_version":"1.0","source":{"id":"2204.00716","kind":"arxiv","version":2}},"canonical_sha256":"920919f1ea2fda1f398b53c05d41ccc43a4a83199f7150750a12900cdec94254","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"920919f1ea2fda1f398b53c05d41ccc43a4a83199f7150750a12900cdec94254","first_computed_at":"2026-07-05T04:17:39.930078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:39.930078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N17Tx7CLTQiO0MRGv+AG8R1Vo7raVWgOfQdGZTtIcpET8RZyg8jxFQetR/sqj6eTYs/kYV7hW0BXokKJypWsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:39.930566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcb9747aa89626f910ce87974f22a75c626877ca3f48445fc33d23fd67f013a8","sha256:ccfff8b65280e04e949a3cd1e0c27639a90368125bbba6861c80f0e70fdd66f7"],"state_sha256":"c0002e8d64a4f2dce004f7ee7cd75c53ea8985efeb0bb2f8c4f4b8338e2738b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bchMUV0RR2OsQ70Cmj88u8LP6TlG+s53vrK3IHN/h6aueUDp69kPlkxkdgDNykqm0NBT50sFGvEir0g2POLDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:28:18.598683Z","bundle_sha256":"b517ee75ad6ea29a72843f5df24fb59037167420407f2a7c665698050a104285"}}