{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:WDBIEWFM54IBUOGGAU2EYVVZEK","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":"d256366254f777dc1290c112f7544c069e33e0f53920722758b11ca277b89b5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-09-18T12:38:34Z","title_canon_sha256":"270431a4fd34810882939a7939463ef11e45674aa97ede495aeac36e3ae50ae2"},"schema_version":"1.0","source":{"id":"1309.4628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1309.4628","created_at":"2026-05-18T03:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"1309.4628v1","created_at":"2026-05-18T03:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.4628","created_at":"2026-05-18T03:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"WDBIEWFM54IB","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"WDBIEWFM54IBUOGG","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"WDBIEWFM","created_at":"2026-05-18T12:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:d57855f4fb3255899dd7f1655dba90d77a813891e21704a7f05945d5f0bbeff6","target":"graph","created_at":"2026-05-18T03:12:58Z","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":"Learning word representations has recently seen much success in computational linguistics. However, assuming sequences of word tokens as input to linguistic analysis is often unjustified. For many languages word segmentation is a non-trivial task and naturally occurring text is sometimes a mixture of natural language strings and other character data. We propose to learn text representations directly from raw character sequences by training a Simple recurrent Network to predict the next character in text. The network uses its hidden layer to evolve abstract representations of the character sequ","authors_text":"Grzegorz Chrupa{\\l}a","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-09-18T12:38:34Z","title":"Text segmentation with character-level text embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.4628","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":"sha256:976e4631d58a80be0abaef2d674e8ec2f823d0a9b919323ff76c60c1207c3130","target":"record","created_at":"2026-05-18T03:12:58Z","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":"d256366254f777dc1290c112f7544c069e33e0f53920722758b11ca277b89b5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-09-18T12:38:34Z","title_canon_sha256":"270431a4fd34810882939a7939463ef11e45674aa97ede495aeac36e3ae50ae2"},"schema_version":"1.0","source":{"id":"1309.4628","kind":"arxiv","version":1}},"canonical_sha256":"b0c28258acef101a38c605344c56b9228917324cf22d82d350ade87f7852e0f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0c28258acef101a38c605344c56b9228917324cf22d82d350ade87f7852e0f9","first_computed_at":"2026-05-18T03:12:58.777457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:12:58.777457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IEk4OoenorDGX9t+szowNnZWqPYj4aRLcrNlq5tWHWskJKnwR1DbZCmUjaEkHCQm9/VGouEO0Ar/M9pm5peZAw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:12:58.778249Z","signed_message":"canonical_sha256_bytes"},"source_id":"1309.4628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:976e4631d58a80be0abaef2d674e8ec2f823d0a9b919323ff76c60c1207c3130","sha256:d57855f4fb3255899dd7f1655dba90d77a813891e21704a7f05945d5f0bbeff6"],"state_sha256":"3b733bf11d95d9fefad7c9c47d800b4bf15b941c3ed34e50f0bc791795e7fde9"}