{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FIXSMVYQLCYB2ZGL3HYQQ4BLIO","short_pith_number":"pith:FIXSMVYQ","schema_version":"1.0","canonical_sha256":"2a2f26571058b01d64cbd9f108702b43b4b67d2eb76b28514ac83f3a716870ab","source":{"kind":"arxiv","id":"1703.03097","version":1},"attestation_state":"computed","paper":{"title":"Information Extraction in Illicit Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mayank Kejriwal, Pedro Szekely","submitted_at":"2017-03-09T01:28:00Z","abstract_excerpt":"Extracting useful entities and attribute values from illicit domains such as human trafficking is a challenging problem with the potential for widespread social impact. Such domains employ atypical language models, have `long tails' and suffer from the problem of concept drift. In this paper, we propose a lightweight, feature-agnostic Information Extraction (IE) paradigm specifically designed for such domains. Our approach uses raw, unlabeled text from an initial corpus, and a few (12-120) seed annotations per domain-specific attribute, to learn robust IE models for unobserved pages and websit"},"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":"1703.03097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-09T01:28:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e2d0558fb3612b94b7c487abe626618d8928edc42071201227649fca28a34e8","abstract_canon_sha256":"d4718bdf54827b0d3667521309d81e909b04eb14750e7b8edca6461feec113eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:01.561651Z","signature_b64":"XuND/IO+yEyQcZyyUprMztgwWzDcT8YQeyHEkd55OocfIoNMC1GYdImNsA52H52IB9tP07MBNoqORicyrDvaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a2f26571058b01d64cbd9f108702b43b4b67d2eb76b28514ac83f3a716870ab","last_reissued_at":"2026-05-18T00:49:01.561023Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:01.561023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information Extraction in Illicit Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mayank Kejriwal, Pedro Szekely","submitted_at":"2017-03-09T01:28:00Z","abstract_excerpt":"Extracting useful entities and attribute values from illicit domains such as human trafficking is a challenging problem with the potential for widespread social impact. Such domains employ atypical language models, have `long tails' and suffer from the problem of concept drift. In this paper, we propose a lightweight, feature-agnostic Information Extraction (IE) paradigm specifically designed for such domains. Our approach uses raw, unlabeled text from an initial corpus, and a few (12-120) seed annotations per domain-specific attribute, to learn robust IE models for unobserved pages and websit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03097","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":"1703.03097","created_at":"2026-05-18T00:49:01.561121+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.03097v1","created_at":"2026-05-18T00:49:01.561121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03097","created_at":"2026-05-18T00:49:01.561121+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIXSMVYQLCYB","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIXSMVYQLCYB2ZGL","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIXSMVYQ","created_at":"2026-05-18T12:31:15.632608+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/FIXSMVYQLCYB2ZGL3HYQQ4BLIO","json":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO.json","graph_json":"https://pith.science/api/pith-number/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/graph.json","events_json":"https://pith.science/api/pith-number/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/events.json","paper":"https://pith.science/paper/FIXSMVYQ"},"agent_actions":{"view_html":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO","download_json":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO.json","view_paper":"https://pith.science/paper/FIXSMVYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.03097&json=true","fetch_graph":"https://pith.science/api/pith-number/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/graph.json","fetch_events":"https://pith.science/api/pith-number/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/action/storage_attestation","attest_author":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/action/author_attestation","sign_citation":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/action/citation_signature","submit_replication":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/action/replication_record"}},"created_at":"2026-05-18T00:49:01.561121+00:00","updated_at":"2026-05-18T00:49:01.561121+00:00"}