{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BDRNE72N7V7MQXFPZUCWXAUAAO","short_pith_number":"pith:BDRNE72N","canonical_record":{"source":{"id":"2302.09207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T02:06:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b34d8ab4777f9dd118b14d0bb98f25b9e8faf63ee69c15c9cd6f44bf643af89","abstract_canon_sha256":"21c6e7b4606381a01f32c86d741d92239406a155633855ea4a6eee3862ca9176"},"schema_version":"1.0"},"canonical_sha256":"08e2d27f4dfd7ec85cafcd056b8280039753f3ea8d9700cd21d69e2afef6f1d6","source":{"kind":"arxiv","id":"2302.09207","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.09207","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2302.09207v3","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09207","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"BDRNE72N7V7M","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"BDRNE72N7V7MQXFP","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"BDRNE72N","created_at":"2026-07-05T08:10:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BDRNE72N7V7MQXFPZUCWXAUAAO","target":"record","payload":{"canonical_record":{"source":{"id":"2302.09207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T02:06:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b34d8ab4777f9dd118b14d0bb98f25b9e8faf63ee69c15c9cd6f44bf643af89","abstract_canon_sha256":"21c6e7b4606381a01f32c86d741d92239406a155633855ea4a6eee3862ca9176"},"schema_version":"1.0"},"canonical_sha256":"08e2d27f4dfd7ec85cafcd056b8280039753f3ea8d9700cd21d69e2afef6f1d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:54.492181Z","signature_b64":"Fcxdv8glBeEZd7pQMgmHgzsXfAcq7CnlPrd6+h/E2WAIH7wdt7rUfdBzUsLXapSt38qHel2snygJgYK7b5DDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08e2d27f4dfd7ec85cafcd056b8280039753f3ea8d9700cd21d69e2afef6f1d6","last_reissued_at":"2026-07-05T08:10:54.491638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:54.491638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.09207","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5O3+QX6uPsu8FuxgMKKfZAPG2E3sDsMIzAP84BMBfg9vG6NuRlMPKmDRRLX5rWbfmS6s0cZebvlzHY4BxJAGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:49:00.883171Z"},"content_sha256":"2636e10c809c2418421e33bdd867a9d25c29882adcdf3e862bee5546b50d1824","schema_version":"1.0","event_id":"sha256:2636e10c809c2418421e33bdd867a9d25c29882adcdf3e862bee5546b50d1824"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BDRNE72N7V7MQXFPZUCWXAUAAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RETVec: Resilient and Efficient Text Vectorizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexey Kurakin, Elie Bursztein, Marina Zhang, Owen Vallis, Xinyu Jia","submitted_at":"2023-02-18T02:06:52Z","abstract_excerpt":"This paper describes RETVec, an efficient, resilient, and multilingual text vectorizer designed for neural-based text processing. RETVec combines a novel character encoding with an optional small embedding model to embed words into a 256-dimensional vector space. The RETVec embedding model is pre-trained using pair-wise metric learning to be robust against typos and character-level adversarial attacks. In this paper, we evaluate and compare RETVec to state-of-the-art vectorizers and word embeddings on popular model architectures and datasets. These comparisons demonstrate that RETVec leads to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09207","kind":"arxiv","version":3},"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/2302.09207/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":"2026-07-05T08:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fcFUk7bhM7WBs3MecvI4TZLlngZANM5n5szpaYWOfEJYZcelUmnBGGBvJP+pB0blMSBLcUvnrVUmhQu1B1dTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:49:00.884257Z"},"content_sha256":"0136c4aaa1b3d80d9d8c50f7660d530fbb845249dadb9f5e9df54cd1988315f3","schema_version":"1.0","event_id":"sha256:0136c4aaa1b3d80d9d8c50f7660d530fbb845249dadb9f5e9df54cd1988315f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BDRNE72N7V7MQXFPZUCWXAUAAO/bundle.json","state_url":"https://pith.science/pith/BDRNE72N7V7MQXFPZUCWXAUAAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BDRNE72N7V7MQXFPZUCWXAUAAO/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":"2026-08-19T16:49:00Z","links":{"resolver":"https://pith.science/pith/BDRNE72N7V7MQXFPZUCWXAUAAO","bundle":"https://pith.science/pith/BDRNE72N7V7MQXFPZUCWXAUAAO/bundle.json","state":"https://pith.science/pith/BDRNE72N7V7MQXFPZUCWXAUAAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BDRNE72N7V7MQXFPZUCWXAUAAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BDRNE72N7V7MQXFPZUCWXAUAAO","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":"21c6e7b4606381a01f32c86d741d92239406a155633855ea4a6eee3862ca9176","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T02:06:52Z","title_canon_sha256":"9b34d8ab4777f9dd118b14d0bb98f25b9e8faf63ee69c15c9cd6f44bf643af89"},"schema_version":"1.0","source":{"id":"2302.09207","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.09207","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2302.09207v3","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09207","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"BDRNE72N7V7M","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"BDRNE72N7V7MQXFP","created_at":"2026-07-05T08:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"BDRNE72N","created_at":"2026-07-05T08:10:54Z"}],"graph_snapshots":[{"event_id":"sha256:0136c4aaa1b3d80d9d8c50f7660d530fbb845249dadb9f5e9df54cd1988315f3","target":"graph","created_at":"2026-07-05T08:10:54Z","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/2302.09207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes RETVec, an efficient, resilient, and multilingual text vectorizer designed for neural-based text processing. RETVec combines a novel character encoding with an optional small embedding model to embed words into a 256-dimensional vector space. The RETVec embedding model is pre-trained using pair-wise metric learning to be robust against typos and character-level adversarial attacks. In this paper, we evaluate and compare RETVec to state-of-the-art vectorizers and word embeddings on popular model architectures and datasets. These comparisons demonstrate that RETVec leads to ","authors_text":"Alexey Kurakin, Elie Bursztein, Marina Zhang, Owen Vallis, Xinyu Jia","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T02:06:52Z","title":"RETVec: Resilient and Efficient Text Vectorizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09207","kind":"arxiv","version":3},"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":"sha256:2636e10c809c2418421e33bdd867a9d25c29882adcdf3e862bee5546b50d1824","target":"record","created_at":"2026-07-05T08:10:54Z","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":"21c6e7b4606381a01f32c86d741d92239406a155633855ea4a6eee3862ca9176","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T02:06:52Z","title_canon_sha256":"9b34d8ab4777f9dd118b14d0bb98f25b9e8faf63ee69c15c9cd6f44bf643af89"},"schema_version":"1.0","source":{"id":"2302.09207","kind":"arxiv","version":3}},"canonical_sha256":"08e2d27f4dfd7ec85cafcd056b8280039753f3ea8d9700cd21d69e2afef6f1d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08e2d27f4dfd7ec85cafcd056b8280039753f3ea8d9700cd21d69e2afef6f1d6","first_computed_at":"2026-07-05T08:10:54.491638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:54.491638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fcxdv8glBeEZd7pQMgmHgzsXfAcq7CnlPrd6+h/E2WAIH7wdt7rUfdBzUsLXapSt38qHel2snygJgYK7b5DDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:54.492181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.09207","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2636e10c809c2418421e33bdd867a9d25c29882adcdf3e862bee5546b50d1824","sha256:0136c4aaa1b3d80d9d8c50f7660d530fbb845249dadb9f5e9df54cd1988315f3"],"state_sha256":"710d8c878a086d30882653a48d5b2267b37dc3c75378ea0db50f2198f19ef5be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuIu5I7XtmvxRPoH9KbeBuQ741mDMvwsyIUQzglXVG7t503ut1cjkHIE1x5nP5Va8Zqdw3fU6qS5iiZUY+zVBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:49:00.890159Z","bundle_sha256":"db8907cdb96f8ae82719eae55f516b08ebdb7196d1972a1d259215d7694594c4"}}