{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LHUNSZKUPIWM7FKVXCIWG3VX5J","short_pith_number":"pith:LHUNSZKU","schema_version":"1.0","canonical_sha256":"59e8d965547a2ccf9555b891636eb7ea7118a6f17ce078c4496463c0c8020560","source":{"kind":"arxiv","id":"2402.01577","version":1},"attestation_state":"computed","paper":{"title":"Deep Active Learning for Data Mining from Conflict Text Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.CY","authors_text":"Mihai Croicu","submitted_at":"2024-02-02T17:16:23Z","abstract_excerpt":"High-resolution event data on armed conflict and related processes have revolutionized the study of political contention with datasets like UCDP GED, ACLED etc. However, most of these datasets limit themselves to collecting spatio-temporal (high-resolution) and intensity data. Information on dynamics, such as targets, tactics, purposes etc. are rarely collected owing to the extreme workload of collecting data. However, most datasets rely on a rich corpus of textual data allowing further mining of further information connected to each event. This paper proposes one such approach that is inexpen"},"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":"2402.01577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-02-02T17:16:23Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"5fb3a8d915f7a53ef80cd51d792dc724a76fcbcdf119641828c1eed56973db74","abstract_canon_sha256":"e7a5ea9d2b31d2b037eb0d60f6f59f6687aa897d5d3fe9fc5ba09d63f97098fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:46.057132Z","signature_b64":"U8G2HJtoQIBfv6QPD/hxueqTk0VvNK4QcidhNeWwLjHORaj8ft/62cP6kq4OHLa4p30knBF5D0WBZlwB/jiUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59e8d965547a2ccf9555b891636eb7ea7118a6f17ce078c4496463c0c8020560","last_reissued_at":"2026-07-05T07:40:46.056743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:46.056743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Active Learning for Data Mining from Conflict Text Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.CY","authors_text":"Mihai Croicu","submitted_at":"2024-02-02T17:16:23Z","abstract_excerpt":"High-resolution event data on armed conflict and related processes have revolutionized the study of political contention with datasets like UCDP GED, ACLED etc. However, most of these datasets limit themselves to collecting spatio-temporal (high-resolution) and intensity data. Information on dynamics, such as targets, tactics, purposes etc. are rarely collected owing to the extreme workload of collecting data. However, most datasets rely on a rich corpus of textual data allowing further mining of further information connected to each event. This paper proposes one such approach that is inexpen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01577","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/2402.01577/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":"2402.01577","created_at":"2026-07-05T07:40:46.056802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01577v1","created_at":"2026-07-05T07:40:46.056802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01577","created_at":"2026-07-05T07:40:46.056802+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHUNSZKUPIWM","created_at":"2026-07-05T07:40:46.056802+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHUNSZKUPIWM7FKV","created_at":"2026-07-05T07:40:46.056802+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHUNSZKU","created_at":"2026-07-05T07:40:46.056802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15060","citing_title":"ConfliBERT: A Language Model for Political Conflict","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J","json":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J.json","graph_json":"https://pith.science/api/pith-number/LHUNSZKUPIWM7FKVXCIWG3VX5J/graph.json","events_json":"https://pith.science/api/pith-number/LHUNSZKUPIWM7FKVXCIWG3VX5J/events.json","paper":"https://pith.science/paper/LHUNSZKU"},"agent_actions":{"view_html":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J","download_json":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J.json","view_paper":"https://pith.science/paper/LHUNSZKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01577&json=true","fetch_graph":"https://pith.science/api/pith-number/LHUNSZKUPIWM7FKVXCIWG3VX5J/graph.json","fetch_events":"https://pith.science/api/pith-number/LHUNSZKUPIWM7FKVXCIWG3VX5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J/action/storage_attestation","attest_author":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J/action/author_attestation","sign_citation":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J/action/citation_signature","submit_replication":"https://pith.science/pith/LHUNSZKUPIWM7FKVXCIWG3VX5J/action/replication_record"}},"created_at":"2026-07-05T07:40:46.056802+00:00","updated_at":"2026-07-05T07:40:46.056802+00:00"}