{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:B23W2PCNRWOHN4DJG55QZTK5ZP","short_pith_number":"pith:B23W2PCN","schema_version":"1.0","canonical_sha256":"0eb76d3c4d8d9c76f069377b0ccd5dcbc55a14d5fa7e6b11e7bdaffb77aef983","source":{"kind":"arxiv","id":"1503.01190","version":1},"attestation_state":"computed","paper":{"title":"Statistical modality tagging from rule-based annotations and crowdsourcing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Bonnie Dorr, Christine D. Piatko, Lori Levin, Michael Bloodgood, Mona Diab, Owen Rambow, Vinodkumar Prabhakaran","submitted_at":"2015-03-04T01:34:36Z","abstract_excerpt":"We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for the overwhelming majority of sentences. We investigate an approach to automatically training a modality tagger where we first gathered sentences based on a high-recall simple rule-based modality tagger and then provided these sentences to Mechanical Turk annotators for further 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":"1503.01190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-04T01:34:36Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6083257a55fbed18c896ceac69b04dc486ac48c92af6531709fb56c443190148","abstract_canon_sha256":"9b1063d5a4510b6ff114b7da79375b68e4b04534cd36746ae8c36b60bb42c5eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:29.649337Z","signature_b64":"O2Qpk4cdbs/W7LxqW1ci5joPYz5CLv8yWCIRUEpQGmD75vmiAaB4Vka4DYGep3Rq18jYxjv7vCSs4sUNXFrLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eb76d3c4d8d9c76f069377b0ccd5dcbc55a14d5fa7e6b11e7bdaffb77aef983","last_reissued_at":"2026-05-18T01:20:29.648628Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:29.648628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical modality tagging from rule-based annotations and crowdsourcing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Bonnie Dorr, Christine D. Piatko, Lori Levin, Michael Bloodgood, Mona Diab, Owen Rambow, Vinodkumar Prabhakaran","submitted_at":"2015-03-04T01:34:36Z","abstract_excerpt":"We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for the overwhelming majority of sentences. We investigate an approach to automatically training a modality tagger where we first gathered sentences based on a high-recall simple rule-based modality tagger and then provided these sentences to Mechanical Turk annotators for further a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.01190","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":""},"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":"1503.01190","created_at":"2026-05-18T01:20:29.648726+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.01190v1","created_at":"2026-05-18T01:20:29.648726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.01190","created_at":"2026-05-18T01:20:29.648726+00:00"},{"alias_kind":"pith_short_12","alias_value":"B23W2PCNRWOH","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"B23W2PCNRWOHN4DJ","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"B23W2PCN","created_at":"2026-05-18T12:29:14.074870+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/B23W2PCNRWOHN4DJG55QZTK5ZP","json":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP.json","graph_json":"https://pith.science/api/pith-number/B23W2PCNRWOHN4DJG55QZTK5ZP/graph.json","events_json":"https://pith.science/api/pith-number/B23W2PCNRWOHN4DJG55QZTK5ZP/events.json","paper":"https://pith.science/paper/B23W2PCN"},"agent_actions":{"view_html":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP","download_json":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP.json","view_paper":"https://pith.science/paper/B23W2PCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.01190&json=true","fetch_graph":"https://pith.science/api/pith-number/B23W2PCNRWOHN4DJG55QZTK5ZP/graph.json","fetch_events":"https://pith.science/api/pith-number/B23W2PCNRWOHN4DJG55QZTK5ZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP/action/storage_attestation","attest_author":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP/action/author_attestation","sign_citation":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP/action/citation_signature","submit_replication":"https://pith.science/pith/B23W2PCNRWOHN4DJG55QZTK5ZP/action/replication_record"}},"created_at":"2026-05-18T01:20:29.648726+00:00","updated_at":"2026-05-18T01:20:29.648726+00:00"}