{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2JNXWRPNL5DJQF6A5HOWC6XQ4Y","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":"7cfa63a24a017462b05cd78d5373d34e6046f108b3820f1f375313cd275df882","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T13:28:33Z","title_canon_sha256":"55b472514025ab9d24330b38edcdb728350d28091626bcbe49b16c095b0d24cd"},"schema_version":"1.0","source":{"id":"1906.00790","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00790","created_at":"2026-05-17T23:43:22Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00790v2","created_at":"2026-05-17T23:43:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00790","created_at":"2026-05-17T23:43:22Z"},{"alias_kind":"pith_short_12","alias_value":"2JNXWRPNL5DJ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2JNXWRPNL5DJQF6A","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2JNXWRPN","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:92a4da77447c9b25e2581108638bd86763469e490ea9935098fb9b710b6f8618","target":"graph","created_at":"2026-05-17T23:43:22Z","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":"Hashtags are often employed on social media and beyond to add metadata to a textual utterance with the goal of increasing discoverability, aiding search, or providing additional semantics. However, the semantic content of hashtags is not straightforward to infer as these represent ad-hoc conventions which frequently include multiple words joined together and can include abbreviations and unorthodox spellings. We build a dataset of 12,594 hashtags split into individual segments and propose a set of approaches for hashtag segmentation by framing it as a pairwise ranking problem between candidate","authors_text":"Daniel Preo\\c{t}iuc-Pietro, Mounica Maddela, Wei Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T13:28:33Z","title":"Multi-task Pairwise Neural Ranking for Hashtag Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00790","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":"sha256:34517f7a1bc56de5e45860ef02ce03e14995b6442ed96aad4877f09edd76e27b","target":"record","created_at":"2026-05-17T23:43:22Z","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":"7cfa63a24a017462b05cd78d5373d34e6046f108b3820f1f375313cd275df882","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T13:28:33Z","title_canon_sha256":"55b472514025ab9d24330b38edcdb728350d28091626bcbe49b16c095b0d24cd"},"schema_version":"1.0","source":{"id":"1906.00790","kind":"arxiv","version":2}},"canonical_sha256":"d25b7b45ed5f469817c0e9dd617af0e60bf4e62f24d0438e3f3d948a379929a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d25b7b45ed5f469817c0e9dd617af0e60bf4e62f24d0438e3f3d948a379929a7","first_computed_at":"2026-05-17T23:43:22.813157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:22.813157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N5Enh/K2zwB6hGCS2Mcyxxf6718LpgXl6bXPviGXzmEJ9Z84fXEWYzR52X1pUPyAzBfDmDVgRLf/8YhEviGhDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:22.813709Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00790","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34517f7a1bc56de5e45860ef02ce03e14995b6442ed96aad4877f09edd76e27b","sha256:92a4da77447c9b25e2581108638bd86763469e490ea9935098fb9b710b6f8618"],"state_sha256":"186b7f2ca1dcc75fdc72d802a446d09ef6b64f0c6c56c16ee3be86b49bffbf12"}