{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:XD233KBUMRZL36NGFMVH3HTVNW","short_pith_number":"pith:XD233KBU","canonical_record":{"source":{"id":"1512.00103","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-01T00:23:44Z","cross_cats_sorted":[],"title_canon_sha256":"fdbc36885ea30780d140d4c7fdce000e8b2e83fa4010892f19c508357f8c71b5","abstract_canon_sha256":"9407b5a8f76f5e773208aef7e019583ad44623c45c2f552641d629d96dc4b035"},"schema_version":"1.0"},"canonical_sha256":"b8f5bda8346472bdf9a62b2a7d9e756d8f6f6e43ea02a81a828880bfe98f4ccf","source":{"kind":"arxiv","id":"1512.00103","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.00103","created_at":"2026-05-18T01:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1512.00103v2","created_at":"2026-05-18T01:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.00103","created_at":"2026-05-18T01:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"XD233KBUMRZL","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XD233KBUMRZL36NG","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XD233KBU","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:XD233KBUMRZL36NGFMVH3HTVNW","target":"record","payload":{"canonical_record":{"source":{"id":"1512.00103","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-01T00:23:44Z","cross_cats_sorted":[],"title_canon_sha256":"fdbc36885ea30780d140d4c7fdce000e8b2e83fa4010892f19c508357f8c71b5","abstract_canon_sha256":"9407b5a8f76f5e773208aef7e019583ad44623c45c2f552641d629d96dc4b035"},"schema_version":"1.0"},"canonical_sha256":"b8f5bda8346472bdf9a62b2a7d9e756d8f6f6e43ea02a81a828880bfe98f4ccf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:52.154177Z","signature_b64":"Xcu4jMAsN18FmCquD66iLwmJkJslaRy9mr5WOzggihI6gQwzbxknznetb+36gMW2y/SXhFGHZzS9e9SUTMR2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8f5bda8346472bdf9a62b2a7d9e756d8f6f6e43ea02a81a828880bfe98f4ccf","last_reissued_at":"2026-05-18T01:17:52.153494Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:52.153494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.00103","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":"2026-05-18T01:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIESfesrmd77jULUn4qMfaik8Ck0i7L7n6HzbLaOz9gIuGllcSdJF1JAiXo8DRwPokJQbVpe52v32OdK6RFDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:40:40.796550Z"},"content_sha256":"f4763a2916955b52f9ea19050219f673eaf3235f48253384e02099d6571e4e03","schema_version":"1.0","event_id":"sha256:f4763a2916955b52f9ea19050219f673eaf3235f48253384e02099d6571e4e03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:XD233KBUMRZL36NGFMVH3HTVNW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Language Processing From Bytes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amarnag Subramanya, Cliff Brunk, Dan Gillick, Oriol Vinyals","submitted_at":"2015-12-01T00:23:44Z","abstract_excerpt":"We describe an LSTM-based model which we call Byte-to-Span (BTS) that reads text as bytes and outputs span annotations of the form [start, length, label] where start positions, lengths, and labels are separate entries in our vocabulary. Because we operate directly on unicode bytes rather than language-specific words or characters, we can analyze text in many languages with a single model. Due to the small vocabulary size, these multilingual models are very compact, but produce results similar to or better than the state-of- the-art in Part-of-Speech tagging and Named Entity Recognition that us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.00103","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":""},"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":"2026-05-18T01:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59RrJyLlkAx+5l7V6gxVBAoXTmQSTelvbKcgelHIS9YPtCMZwWxMKAgRHuAoLkxprjnGrYlaadsvIIr9tEJxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:40:40.796900Z"},"content_sha256":"96edf79990d7b048ce0830a4c84fee8654319b07d126bb3c3789f083516a62ee","schema_version":"1.0","event_id":"sha256:96edf79990d7b048ce0830a4c84fee8654319b07d126bb3c3789f083516a62ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XD233KBUMRZL36NGFMVH3HTVNW/bundle.json","state_url":"https://pith.science/pith/XD233KBUMRZL36NGFMVH3HTVNW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XD233KBUMRZL36NGFMVH3HTVNW/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":"2026-05-30T08:40:40Z","links":{"resolver":"https://pith.science/pith/XD233KBUMRZL36NGFMVH3HTVNW","bundle":"https://pith.science/pith/XD233KBUMRZL36NGFMVH3HTVNW/bundle.json","state":"https://pith.science/pith/XD233KBUMRZL36NGFMVH3HTVNW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XD233KBUMRZL36NGFMVH3HTVNW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:XD233KBUMRZL36NGFMVH3HTVNW","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":"9407b5a8f76f5e773208aef7e019583ad44623c45c2f552641d629d96dc4b035","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-01T00:23:44Z","title_canon_sha256":"fdbc36885ea30780d140d4c7fdce000e8b2e83fa4010892f19c508357f8c71b5"},"schema_version":"1.0","source":{"id":"1512.00103","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.00103","created_at":"2026-05-18T01:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1512.00103v2","created_at":"2026-05-18T01:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.00103","created_at":"2026-05-18T01:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"XD233KBUMRZL","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XD233KBUMRZL36NG","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XD233KBU","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:96edf79990d7b048ce0830a4c84fee8654319b07d126bb3c3789f083516a62ee","target":"graph","created_at":"2026-05-18T01:17:52Z","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"},"paper":{"abstract_excerpt":"We describe an LSTM-based model which we call Byte-to-Span (BTS) that reads text as bytes and outputs span annotations of the form [start, length, label] where start positions, lengths, and labels are separate entries in our vocabulary. Because we operate directly on unicode bytes rather than language-specific words or characters, we can analyze text in many languages with a single model. Due to the small vocabulary size, these multilingual models are very compact, but produce results similar to or better than the state-of- the-art in Part-of-Speech tagging and Named Entity Recognition that us","authors_text":"Amarnag Subramanya, Cliff Brunk, Dan Gillick, Oriol Vinyals","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-01T00:23:44Z","title":"Multilingual Language Processing From Bytes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.00103","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:f4763a2916955b52f9ea19050219f673eaf3235f48253384e02099d6571e4e03","target":"record","created_at":"2026-05-18T01:17:52Z","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":"9407b5a8f76f5e773208aef7e019583ad44623c45c2f552641d629d96dc4b035","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-01T00:23:44Z","title_canon_sha256":"fdbc36885ea30780d140d4c7fdce000e8b2e83fa4010892f19c508357f8c71b5"},"schema_version":"1.0","source":{"id":"1512.00103","kind":"arxiv","version":2}},"canonical_sha256":"b8f5bda8346472bdf9a62b2a7d9e756d8f6f6e43ea02a81a828880bfe98f4ccf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8f5bda8346472bdf9a62b2a7d9e756d8f6f6e43ea02a81a828880bfe98f4ccf","first_computed_at":"2026-05-18T01:17:52.153494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:52.153494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xcu4jMAsN18FmCquD66iLwmJkJslaRy9mr5WOzggihI6gQwzbxknznetb+36gMW2y/SXhFGHZzS9e9SUTMR2Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:52.154177Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.00103","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4763a2916955b52f9ea19050219f673eaf3235f48253384e02099d6571e4e03","sha256:96edf79990d7b048ce0830a4c84fee8654319b07d126bb3c3789f083516a62ee"],"state_sha256":"401925be949f35ff7ebd62ebff8beed554aba305056fa97a6a4498dc0c8388cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fw+bIZxJWMJuQCi2g9jeDx088FWG2q39X4nJV9bgKsDcjUYJn+06GkN55yXLKtNcYz8MvIt9BE4F18hu/b78Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:40:40.799356Z","bundle_sha256":"ccafce9bbbd17933f1f64784601a1c0844999ec496b91cbd3b3fc23f80b0a49b"}}