{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EBRSJEEXLBMAVA5GFDKLXTGNAV","short_pith_number":"pith:EBRSJEEX","canonical_record":{"source":{"id":"2106.13302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-24T20:14:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04ff2ec85127d41d93b59d63dd7deaa9da9e3f379a14885e13e0edad92fea360","abstract_canon_sha256":"49e2a0ab0e08244a5ee866b76652d00f34215c4caf63418b7664e6c6e65055ee"},"schema_version":"1.0"},"canonical_sha256":"206324909758580a83a628d4bbcccd056bfa1b4dc0dd3c63f158dada9e4a57e3","source":{"kind":"arxiv","id":"2106.13302","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13302","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13302v1","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13302","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"EBRSJEEXLBMA","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"EBRSJEEXLBMAVA5G","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"EBRSJEEX","created_at":"2026-07-05T02:52:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EBRSJEEXLBMAVA5GFDKLXTGNAV","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-24T20:14:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04ff2ec85127d41d93b59d63dd7deaa9da9e3f379a14885e13e0edad92fea360","abstract_canon_sha256":"49e2a0ab0e08244a5ee866b76652d00f34215c4caf63418b7664e6c6e65055ee"},"schema_version":"1.0"},"canonical_sha256":"206324909758580a83a628d4bbcccd056bfa1b4dc0dd3c63f158dada9e4a57e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:17.951328Z","signature_b64":"tWDypHhWjJFOiPeKVrQ4VYxKveyYaPzmqT3EKCmdSuqvnEPojvgPLg3v8HVddExQ64Nx95NUzXGFOvTRBzfZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"206324909758580a83a628d4bbcccd056bfa1b4dc0dd3c63f158dada9e4a57e3","last_reissued_at":"2026-07-05T02:52:17.950889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:17.950889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13302","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOC2t3mIWkIiPZ8nt5p7u9NTcacjLVTsPWGMy8SniohBezbnT1zqOsaI0pH94s/g3tFY/nleV+Hvtm+BhRESAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T10:34:03.919227Z"},"content_sha256":"ff401190d2a430066fe882d301f25f95787f9749ae72875bd5d226ad41bfdce4","schema_version":"1.0","event_id":"sha256:ff401190d2a430066fe882d301f25f95787f9749ae72875bd5d226ad41bfdce4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EBRSJEEXLBMAVA5GFDKLXTGNAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"byteSteady: Fast Classification Using Byte-Level n-Gram Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexandre Drouin, Raymond Li, Xiang Zhang","submitted_at":"2021-06-24T20:14:48Z","abstract_excerpt":"This article introduces byteSteady -- a fast model for classification using byte-level n-gram embeddings. byteSteady assumes that each input comes as a sequence of bytes. A representation vector is produced using the averaged embedding vectors of byte-level n-grams, with a pre-defined set of n. The hashing trick is used to reduce the number of embedding vectors. This input representation vector is then fed into a linear classifier. A straightforward application of byteSteady is text classification. We also apply byteSteady to one type of non-language data -- DNA sequences for gene classificati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13302","kind":"arxiv","version":1},"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/2106.13302/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":"2026-07-05T02:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MzfXuAI6ARGN6Q3CYrdRRMZpVDOb9PEg/tNw6HbyZYn08BXI2OZijwuAzFYpgq9ZiHSagD3hjDz4WBHPCMKmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T10:34:03.919797Z"},"content_sha256":"f25baca70748796e35fa4e0dcbbce9f7d6c14a9ded9185adf3cd25cffccb8f99","schema_version":"1.0","event_id":"sha256:f25baca70748796e35fa4e0dcbbce9f7d6c14a9ded9185adf3cd25cffccb8f99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBRSJEEXLBMAVA5GFDKLXTGNAV/bundle.json","state_url":"https://pith.science/pith/EBRSJEEXLBMAVA5GFDKLXTGNAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBRSJEEXLBMAVA5GFDKLXTGNAV/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":"2026-08-01T10:34:03Z","links":{"resolver":"https://pith.science/pith/EBRSJEEXLBMAVA5GFDKLXTGNAV","bundle":"https://pith.science/pith/EBRSJEEXLBMAVA5GFDKLXTGNAV/bundle.json","state":"https://pith.science/pith/EBRSJEEXLBMAVA5GFDKLXTGNAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBRSJEEXLBMAVA5GFDKLXTGNAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EBRSJEEXLBMAVA5GFDKLXTGNAV","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":"49e2a0ab0e08244a5ee866b76652d00f34215c4caf63418b7664e6c6e65055ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-24T20:14:48Z","title_canon_sha256":"04ff2ec85127d41d93b59d63dd7deaa9da9e3f379a14885e13e0edad92fea360"},"schema_version":"1.0","source":{"id":"2106.13302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13302","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13302v1","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13302","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"EBRSJEEXLBMA","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"EBRSJEEXLBMAVA5G","created_at":"2026-07-05T02:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"EBRSJEEX","created_at":"2026-07-05T02:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:f25baca70748796e35fa4e0dcbbce9f7d6c14a9ded9185adf3cd25cffccb8f99","target":"graph","created_at":"2026-07-05T02:52:17Z","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/2106.13302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This article introduces byteSteady -- a fast model for classification using byte-level n-gram embeddings. byteSteady assumes that each input comes as a sequence of bytes. A representation vector is produced using the averaged embedding vectors of byte-level n-grams, with a pre-defined set of n. The hashing trick is used to reduce the number of embedding vectors. This input representation vector is then fed into a linear classifier. A straightforward application of byteSteady is text classification. We also apply byteSteady to one type of non-language data -- DNA sequences for gene classificati","authors_text":"Alexandre Drouin, Raymond Li, Xiang Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-24T20:14:48Z","title":"byteSteady: Fast Classification Using Byte-Level n-Gram Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13302","kind":"arxiv","version":1},"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:ff401190d2a430066fe882d301f25f95787f9749ae72875bd5d226ad41bfdce4","target":"record","created_at":"2026-07-05T02:52:17Z","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":"49e2a0ab0e08244a5ee866b76652d00f34215c4caf63418b7664e6c6e65055ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-24T20:14:48Z","title_canon_sha256":"04ff2ec85127d41d93b59d63dd7deaa9da9e3f379a14885e13e0edad92fea360"},"schema_version":"1.0","source":{"id":"2106.13302","kind":"arxiv","version":1}},"canonical_sha256":"206324909758580a83a628d4bbcccd056bfa1b4dc0dd3c63f158dada9e4a57e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"206324909758580a83a628d4bbcccd056bfa1b4dc0dd3c63f158dada9e4a57e3","first_computed_at":"2026-07-05T02:52:17.950889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:17.950889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tWDypHhWjJFOiPeKVrQ4VYxKveyYaPzmqT3EKCmdSuqvnEPojvgPLg3v8HVddExQ64Nx95NUzXGFOvTRBzfZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:17.951328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff401190d2a430066fe882d301f25f95787f9749ae72875bd5d226ad41bfdce4","sha256:f25baca70748796e35fa4e0dcbbce9f7d6c14a9ded9185adf3cd25cffccb8f99"],"state_sha256":"69524a3f7f38a4be4bb3fa0ffaa8c812e9cbdb16c3f63a34f4aca1b7597c8185"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ATDK+xaYnIaIpO1h4cdfDi6DPssEF6xVCvVyiqoZlKc56hT1joz/SU3cdVhe6KJXRB/9NnK+7/Mft2mMKqVDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T10:34:03.925707Z","bundle_sha256":"e8ba4d215973ac383ddfa17f7b570b0d11e39fe083a8bd13dc079d38ebe48246"}}