{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FIXSMVYQLCYB2ZGL3HYQQ4BLIO","short_pith_number":"pith:FIXSMVYQ","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"},"canonical_sha256":"2a2f26571058b01d64cbd9f108702b43b4b67d2eb76b28514ac83f3a716870ab","source":{"kind":"arxiv","id":"1703.03097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03097","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03097v1","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03097","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"FIXSMVYQLCYB","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FIXSMVYQLCYB2ZGL","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FIXSMVYQ","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FIXSMVYQLCYB2ZGL3HYQQ4BLIO","target":"record","payload":{"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"},"canonical_sha256":"2a2f26571058b01d64cbd9f108702b43b4b67d2eb76b28514ac83f3a716870ab","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"},"source_kind":"arxiv","source_id":"1703.03097","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8m02QwOCp4aFlYs7CmUfYMSefnEx31TUgZsRVi/FvJklfjus0/oYBMKuwn2zArSFtsnhLwKU+DDlE5rSBPnQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:21:03.194657Z"},"content_sha256":"5a4642d11a0d45dd42400851fe068b55ae927394f8f25103aa85db75102484bf","schema_version":"1.0","event_id":"sha256:5a4642d11a0d45dd42400851fe068b55ae927394f8f25103aa85db75102484bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FIXSMVYQLCYB2ZGL3HYQQ4BLIO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Au57ZRgYKa6y1T6oBXnT54EZdrGTbdkaz4oJZv5th0CIdS+GM1Jo/JM/7ye0JctbrFJxot6OrouFaqs2s8NNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:21:03.195209Z"},"content_sha256":"1d69184345771b57c9b86bbed57bee4d7b19a4377535f4e2039f737a06e38aad","schema_version":"1.0","event_id":"sha256:1d69184345771b57c9b86bbed57bee4d7b19a4377535f4e2039f737a06e38aad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/bundle.json","state_url":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T16:21:03Z","links":{"resolver":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO","bundle":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/bundle.json","state":"https://pith.science/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIXSMVYQLCYB2ZGL3HYQQ4BLIO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FIXSMVYQLCYB2ZGL3HYQQ4BLIO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d4718bdf54827b0d3667521309d81e909b04eb14750e7b8edca6461feec113eb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-09T01:28:00Z","title_canon_sha256":"9e2d0558fb3612b94b7c487abe626618d8928edc42071201227649fca28a34e8"},"schema_version":"1.0","source":{"id":"1703.03097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03097","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03097v1","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03097","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"FIXSMVYQLCYB","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FIXSMVYQLCYB2ZGL","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FIXSMVYQ","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:1d69184345771b57c9b86bbed57bee4d7b19a4377535f4e2039f737a06e38aad","target":"graph","created_at":"2026-05-18T00:49:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Mayank Kejriwal, Pedro Szekely","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-09T01:28:00Z","title":"Information Extraction in Illicit Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03097","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5a4642d11a0d45dd42400851fe068b55ae927394f8f25103aa85db75102484bf","target":"record","created_at":"2026-05-18T00:49:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d4718bdf54827b0d3667521309d81e909b04eb14750e7b8edca6461feec113eb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-09T01:28:00Z","title_canon_sha256":"9e2d0558fb3612b94b7c487abe626618d8928edc42071201227649fca28a34e8"},"schema_version":"1.0","source":{"id":"1703.03097","kind":"arxiv","version":1}},"canonical_sha256":"2a2f26571058b01d64cbd9f108702b43b4b67d2eb76b28514ac83f3a716870ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a2f26571058b01d64cbd9f108702b43b4b67d2eb76b28514ac83f3a716870ab","first_computed_at":"2026-05-18T00:49:01.561023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:01.561023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XuND/IO+yEyQcZyyUprMztgwWzDcT8YQeyHEkd55OocfIoNMC1GYdImNsA52H52IB9tP07MBNoqORicyrDvaAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:01.561651Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.03097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a4642d11a0d45dd42400851fe068b55ae927394f8f25103aa85db75102484bf","sha256:1d69184345771b57c9b86bbed57bee4d7b19a4377535f4e2039f737a06e38aad"],"state_sha256":"e49753b574a6c01c97dc330511d78c5d02e06259b983c57e7de97595d6246809"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LsIt80dBdJR92qmpt3znfECKtNhVXZfUFMYGK40IF0BjAHq81Xte5kR1vmuYjiGUwjV1xkO+U4UNCx8ht/TcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T16:21:03.198026Z","bundle_sha256":"ac0de82e21d48b7bd9a7bcb21ee6fa18f1a50377189b1c5e2a82accf05e9f3a4"}}