{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LBV6FXCJRKEWFMOJCTAWGOZYNI","short_pith_number":"pith:LBV6FXCJ","canonical_record":{"source":{"id":"1802.04559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-13T11:04:07Z","cross_cats_sorted":[],"title_canon_sha256":"b1f88a440939275ac3933911c9c18be5943dc92e06c269ef402ddcee206c57bc","abstract_canon_sha256":"aab33b0a81c6fdeafd46c8eaf28c97f9892c667e373cf7bb202e3e058ca98079"},"schema_version":"1.0"},"canonical_sha256":"586be2dc498a8962b1c914c1633b386a2b3eaee8525476df2fa9e531e4d4ac61","source":{"kind":"arxiv","id":"1802.04559","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04559","created_at":"2026-05-18T00:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04559v1","created_at":"2026-05-18T00:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04559","created_at":"2026-05-18T00:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"LBV6FXCJRKEW","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LBV6FXCJRKEWFMOJ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LBV6FXCJ","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LBV6FXCJRKEWFMOJCTAWGOZYNI","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-13T11:04:07Z","cross_cats_sorted":[],"title_canon_sha256":"b1f88a440939275ac3933911c9c18be5943dc92e06c269ef402ddcee206c57bc","abstract_canon_sha256":"aab33b0a81c6fdeafd46c8eaf28c97f9892c667e373cf7bb202e3e058ca98079"},"schema_version":"1.0"},"canonical_sha256":"586be2dc498a8962b1c914c1633b386a2b3eaee8525476df2fa9e531e4d4ac61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:42.109968Z","signature_b64":"oiak2YxxA5IJq58gUcRsMq0o1GJxcLJOXM35bl/blqGWlsqZTp9FpXBQHhEMeEPyPvCdaud0yUWlKaaO+faBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586be2dc498a8962b1c914c1633b386a2b3eaee8525476df2fa9e531e4d4ac61","last_reissued_at":"2026-05-18T00:23:42.109282Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:42.109282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04559","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":"2026-05-18T00:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17epS5Jm77+a/UrCX/3+Q5wSJoroIaxI8ATt9+6pyjbOFf3aNzGlLMzxWFCMnygs0lwNn9ShEdwBntUBjBNLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:49:01.348259Z"},"content_sha256":"93ef97d62d1adacd8f10aaab821cfbfc444c2d9df625a9aa563201c5e5efe9af","schema_version":"1.0","event_id":"sha256:93ef97d62d1adacd8f10aaab821cfbfc444c2d9df625a9aa563201c5e5efe9af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LBV6FXCJRKEWFMOJCTAWGOZYNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sentence Boundary Detection for French with Subword-Level Information Vectors and Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carlos-Emiliano Gonz\\'alez-Gallardo, Juan-Manuel Torres-Moreno","submitted_at":"2018-02-13T11:04:07Z","abstract_excerpt":"In this work we tackle the problem of sentence boundary detection applied to French as a binary classification task (\"sentence boundary\" or \"not sentence boundary\"). We combine convolutional neural networks with subword-level information vectors, which are word embedding representations learned from Wikipedia that take advantage of the words morphology; so each word is represented as a bag of their character n-grams.\n  We decide to use a big written dataset (French Gigaword) instead of standard size transcriptions to train and evaluate the proposed architectures with the intention of using the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04559","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":""},"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":"2026-05-18T00:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTd8T6i6NpIFtvZ3XGTNLkJMNapqSasSF3EGdHx1mT/d4Oqogtl53ezTfNDM9nDuFBVgl3rlpV+LeZGoxyTeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:49:01.349008Z"},"content_sha256":"0916464511f77bd8307ea188d66fc4f41a17b9e133b7beb21ad7c73d03875b1d","schema_version":"1.0","event_id":"sha256:0916464511f77bd8307ea188d66fc4f41a17b9e133b7beb21ad7c73d03875b1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/bundle.json","state_url":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/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":"2026-06-06T06:49:01Z","links":{"resolver":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI","bundle":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/bundle.json","state":"https://pith.science/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBV6FXCJRKEWFMOJCTAWGOZYNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LBV6FXCJRKEWFMOJCTAWGOZYNI","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":"aab33b0a81c6fdeafd46c8eaf28c97f9892c667e373cf7bb202e3e058ca98079","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-13T11:04:07Z","title_canon_sha256":"b1f88a440939275ac3933911c9c18be5943dc92e06c269ef402ddcee206c57bc"},"schema_version":"1.0","source":{"id":"1802.04559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04559","created_at":"2026-05-18T00:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04559v1","created_at":"2026-05-18T00:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04559","created_at":"2026-05-18T00:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"LBV6FXCJRKEW","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LBV6FXCJRKEWFMOJ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LBV6FXCJ","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:0916464511f77bd8307ea188d66fc4f41a17b9e133b7beb21ad7c73d03875b1d","target":"graph","created_at":"2026-05-18T00:23:42Z","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":"In this work we tackle the problem of sentence boundary detection applied to French as a binary classification task (\"sentence boundary\" or \"not sentence boundary\"). We combine convolutional neural networks with subword-level information vectors, which are word embedding representations learned from Wikipedia that take advantage of the words morphology; so each word is represented as a bag of their character n-grams.\n  We decide to use a big written dataset (French Gigaword) instead of standard size transcriptions to train and evaluate the proposed architectures with the intention of using the","authors_text":"Carlos-Emiliano Gonz\\'alez-Gallardo, Juan-Manuel Torres-Moreno","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-13T11:04:07Z","title":"Sentence Boundary Detection for French with Subword-Level Information Vectors and Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04559","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":"sha256:93ef97d62d1adacd8f10aaab821cfbfc444c2d9df625a9aa563201c5e5efe9af","target":"record","created_at":"2026-05-18T00:23:42Z","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":"aab33b0a81c6fdeafd46c8eaf28c97f9892c667e373cf7bb202e3e058ca98079","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-13T11:04:07Z","title_canon_sha256":"b1f88a440939275ac3933911c9c18be5943dc92e06c269ef402ddcee206c57bc"},"schema_version":"1.0","source":{"id":"1802.04559","kind":"arxiv","version":1}},"canonical_sha256":"586be2dc498a8962b1c914c1633b386a2b3eaee8525476df2fa9e531e4d4ac61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"586be2dc498a8962b1c914c1633b386a2b3eaee8525476df2fa9e531e4d4ac61","first_computed_at":"2026-05-18T00:23:42.109282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:42.109282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oiak2YxxA5IJq58gUcRsMq0o1GJxcLJOXM35bl/blqGWlsqZTp9FpXBQHhEMeEPyPvCdaud0yUWlKaaO+faBBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:42.109968Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93ef97d62d1adacd8f10aaab821cfbfc444c2d9df625a9aa563201c5e5efe9af","sha256:0916464511f77bd8307ea188d66fc4f41a17b9e133b7beb21ad7c73d03875b1d"],"state_sha256":"41777cf582d55342b6f7df29298108fa6d273a38ccdc2135c24c106f6b768d19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QuBoePc986Au+d7TO8RsLbuwl1wIzq+BYAa/pZq+Dv0l7vUitm7yB/Z+lx2ZCY78Bwl3BTBJeGV+SY1K2XXYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T06:49:01.353033Z","bundle_sha256":"5b75711ecd98da9fe67e6c61dbc575741758c3939e0cdbc95c1fd5c7b8aec826"}}