{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YQDFPRHFCGV2URZFRAL7QBMZIT","short_pith_number":"pith:YQDFPRHF","schema_version":"1.0","canonical_sha256":"c40657c4e511abaa47258817f8059944c1e1adbd3b5ceed5b704d4041a9d9d3f","source":{"kind":"arxiv","id":"2307.16045","version":1},"attestation_state":"computed","paper":{"title":"Automatic Extraction of the Romanian Academic Word List: Data and Methods","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana-Maria Bucur, Andreea Dinc\\u{a}, M\\u{a}d\\u{a}lina Chitez, Roxana Rogobete","submitted_at":"2023-07-29T18:21:38Z","abstract_excerpt":"This paper presents the methodology and data used for the automatic extraction of the Romanian Academic Word List (Ro-AWL). Academic Word Lists are useful in both L2 and L1 teaching contexts. For the Romanian language, no such resource exists so far. Ro-AWL has been generated by combining methods from corpus and computational linguistics with L2 academic writing approaches. We use two types of data: (a) existing data, such as the Romanian Frequency List based on the ROMBAC corpus, and (b) self-compiled data, such as the expert academic writing corpus EXPRES. For constructing the academic word "},"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":"2307.16045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-29T18:21:38Z","cross_cats_sorted":[],"title_canon_sha256":"449cec96a195144c9902abd1f446557ce73dc91015015ebc0e758fd9598ed46a","abstract_canon_sha256":"71e4da2eb5ad8a94edc4ea6ea0966a452dcf6156a80f57531b496d080aa74103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:58.073759Z","signature_b64":"+UGGm3Amu4xVCWIya3ZEWcd8kQTL60+Pvdo7bsq56MJm/K6gOBlh91UI91QoaWx/7d7LYq4mRpdZgR3mtcfTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40657c4e511abaa47258817f8059944c1e1adbd3b5ceed5b704d4041a9d9d3f","last_reissued_at":"2026-07-05T06:35:58.073399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:58.073399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Extraction of the Romanian Academic Word List: Data and Methods","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana-Maria Bucur, Andreea Dinc\\u{a}, M\\u{a}d\\u{a}lina Chitez, Roxana Rogobete","submitted_at":"2023-07-29T18:21:38Z","abstract_excerpt":"This paper presents the methodology and data used for the automatic extraction of the Romanian Academic Word List (Ro-AWL). Academic Word Lists are useful in both L2 and L1 teaching contexts. For the Romanian language, no such resource exists so far. Ro-AWL has been generated by combining methods from corpus and computational linguistics with L2 academic writing approaches. We use two types of data: (a) existing data, such as the Romanian Frequency List based on the ROMBAC corpus, and (b) self-compiled data, such as the expert academic writing corpus EXPRES. For constructing the academic word "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16045","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/2307.16045/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":"2307.16045","created_at":"2026-07-05T06:35:58.073459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16045v1","created_at":"2026-07-05T06:35:58.073459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16045","created_at":"2026-07-05T06:35:58.073459+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQDFPRHFCGV2","created_at":"2026-07-05T06:35:58.073459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQDFPRHFCGV2URZF","created_at":"2026-07-05T06:35:58.073459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQDFPRHF","created_at":"2026-07-05T06:35:58.073459+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/YQDFPRHFCGV2URZFRAL7QBMZIT","json":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT.json","graph_json":"https://pith.science/api/pith-number/YQDFPRHFCGV2URZFRAL7QBMZIT/graph.json","events_json":"https://pith.science/api/pith-number/YQDFPRHFCGV2URZFRAL7QBMZIT/events.json","paper":"https://pith.science/paper/YQDFPRHF"},"agent_actions":{"view_html":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT","download_json":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT.json","view_paper":"https://pith.science/paper/YQDFPRHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16045&json=true","fetch_graph":"https://pith.science/api/pith-number/YQDFPRHFCGV2URZFRAL7QBMZIT/graph.json","fetch_events":"https://pith.science/api/pith-number/YQDFPRHFCGV2URZFRAL7QBMZIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT/action/storage_attestation","attest_author":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT/action/author_attestation","sign_citation":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT/action/citation_signature","submit_replication":"https://pith.science/pith/YQDFPRHFCGV2URZFRAL7QBMZIT/action/replication_record"}},"created_at":"2026-07-05T06:35:58.073459+00:00","updated_at":"2026-07-05T06:35:58.073459+00:00"}