{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FW6RBCOGSCQV2NAXK3SV5CRRQ6","short_pith_number":"pith:FW6RBCOG","schema_version":"1.0","canonical_sha256":"2dbd1089c690a15d341756e55e8a31879f15c9ef9e227a19313b3a08aee54ee5","source":{"kind":"arxiv","id":"2201.06741","version":1},"attestation_state":"computed","paper":{"title":"HashSet -- A Dataset For Hashtag Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshala Bhatnagar, Manish Shrivastava, Naman Ahuja, Ponnurangam Kumaraguru, Prashant Kodali","submitted_at":"2022-01-18T04:40:45Z","abstract_excerpt":"Hashtag segmentation is the task of breaking a hashtag into its constituent tokens. Hashtags often encode the essence of user-generated posts, along with information like topic and sentiment, which are useful in downstream tasks. Hashtags prioritize brevity and are written in unique ways -- transliterating and mixing languages, spelling variations, creative named entities. Benchmark datasets used for the hashtag segmentation task -- STAN, BOUN -- are small in size and extracted from a single set of tweets. However, datasets should reflect the variations in writing styles of hashtags and also a"},"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":"2201.06741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-18T04:40:45Z","cross_cats_sorted":[],"title_canon_sha256":"1f823711635cd6e4f8cb7fdfab31debb7da0d7f59133e8a9c2c407ba2e661201","abstract_canon_sha256":"4efea67783aed3a1c0373abfa5fccad2a3c32712d86a1cebfa70f502d51e8ac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:49:01.060650Z","signature_b64":"U/G3NM+cyVSzo0N72qI0Jf7LwFCULpbepqh6OE7m/iyK6Tih3DrtK1f1STR9Twrk/JaymtCJYm/BOkjj2jB/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dbd1089c690a15d341756e55e8a31879f15c9ef9e227a19313b3a08aee54ee5","last_reissued_at":"2026-07-05T03:49:01.060252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:49:01.060252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HashSet -- A Dataset For Hashtag Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshala Bhatnagar, Manish Shrivastava, Naman Ahuja, Ponnurangam Kumaraguru, Prashant Kodali","submitted_at":"2022-01-18T04:40:45Z","abstract_excerpt":"Hashtag segmentation is the task of breaking a hashtag into its constituent tokens. Hashtags often encode the essence of user-generated posts, along with information like topic and sentiment, which are useful in downstream tasks. Hashtags prioritize brevity and are written in unique ways -- transliterating and mixing languages, spelling variations, creative named entities. Benchmark datasets used for the hashtag segmentation task -- STAN, BOUN -- are small in size and extracted from a single set of tweets. However, datasets should reflect the variations in writing styles of hashtags and also a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06741","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.06741/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2201.06741","created_at":"2026-07-05T03:49:01.060309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.06741v1","created_at":"2026-07-05T03:49:01.060309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06741","created_at":"2026-07-05T03:49:01.060309+00:00"},{"alias_kind":"pith_short_12","alias_value":"FW6RBCOGSCQV","created_at":"2026-07-05T03:49:01.060309+00:00"},{"alias_kind":"pith_short_16","alias_value":"FW6RBCOGSCQV2NAX","created_at":"2026-07-05T03:49:01.060309+00:00"},{"alias_kind":"pith_short_8","alias_value":"FW6RBCOG","created_at":"2026-07-05T03:49:01.060309+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/FW6RBCOGSCQV2NAXK3SV5CRRQ6","json":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6.json","graph_json":"https://pith.science/api/pith-number/FW6RBCOGSCQV2NAXK3SV5CRRQ6/graph.json","events_json":"https://pith.science/api/pith-number/FW6RBCOGSCQV2NAXK3SV5CRRQ6/events.json","paper":"https://pith.science/paper/FW6RBCOG"},"agent_actions":{"view_html":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6","download_json":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6.json","view_paper":"https://pith.science/paper/FW6RBCOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.06741&json=true","fetch_graph":"https://pith.science/api/pith-number/FW6RBCOGSCQV2NAXK3SV5CRRQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/FW6RBCOGSCQV2NAXK3SV5CRRQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6/action/storage_attestation","attest_author":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6/action/author_attestation","sign_citation":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6/action/citation_signature","submit_replication":"https://pith.science/pith/FW6RBCOGSCQV2NAXK3SV5CRRQ6/action/replication_record"}},"created_at":"2026-07-05T03:49:01.060309+00:00","updated_at":"2026-07-05T03:49:01.060309+00:00"}