{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2JNXWRPNL5DJQF6A5HOWC6XQ4Y","short_pith_number":"pith:2JNXWRPN","schema_version":"1.0","canonical_sha256":"d25b7b45ed5f469817c0e9dd617af0e60bf4e62f24d0438e3f3d948a379929a7","source":{"kind":"arxiv","id":"1906.00790","version":2},"attestation_state":"computed","paper":{"title":"Multi-task Pairwise Neural Ranking for Hashtag Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Preo\\c{t}iuc-Pietro, Mounica Maddela, Wei Xu","submitted_at":"2019-06-03T13:28:33Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1906.00790","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T13:28:33Z","cross_cats_sorted":[],"title_canon_sha256":"55b472514025ab9d24330b38edcdb728350d28091626bcbe49b16c095b0d24cd","abstract_canon_sha256":"7cfa63a24a017462b05cd78d5373d34e6046f108b3820f1f375313cd275df882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:22.813709Z","signature_b64":"N5Enh/K2zwB6hGCS2Mcyxxf6718LpgXl6bXPviGXzmEJ9Z84fXEWYzR52X1pUPyAzBfDmDVgRLf/8YhEviGhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d25b7b45ed5f469817c0e9dd617af0e60bf4e62f24d0438e3f3d948a379929a7","last_reissued_at":"2026-05-17T23:43:22.813157Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:22.813157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task Pairwise Neural Ranking for Hashtag Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Preo\\c{t}iuc-Pietro, Mounica Maddela, Wei Xu","submitted_at":"2019-06-03T13:28:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00790","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.00790","created_at":"2026-05-17T23:43:22.813246+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00790v2","created_at":"2026-05-17T23:43:22.813246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00790","created_at":"2026-05-17T23:43:22.813246+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JNXWRPNL5DJ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JNXWRPNL5DJQF6A","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JNXWRPN","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y","json":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y.json","graph_json":"https://pith.science/api/pith-number/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/graph.json","events_json":"https://pith.science/api/pith-number/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/events.json","paper":"https://pith.science/paper/2JNXWRPN"},"agent_actions":{"view_html":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y","download_json":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y.json","view_paper":"https://pith.science/paper/2JNXWRPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00790&json=true","fetch_graph":"https://pith.science/api/pith-number/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/action/storage_attestation","attest_author":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/action/author_attestation","sign_citation":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/action/citation_signature","submit_replication":"https://pith.science/pith/2JNXWRPNL5DJQF6A5HOWC6XQ4Y/action/replication_record"}},"created_at":"2026-05-17T23:43:22.813246+00:00","updated_at":"2026-05-17T23:43:22.813246+00:00"}