{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:BHRB6NO463A7OMK66TCM37GTVK","short_pith_number":"pith:BHRB6NO4","canonical_record":{"source":{"id":"1504.06650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T21:43:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f4e45ce5b5f454a08d1f98301117af4b3445b270f9ca9c2ca4c66208c314098e","abstract_canon_sha256":"ca5b374f0ebf1313845253a279896ee9ced4c97151f25bc6d667e9fa4e95029d"},"schema_version":"1.0"},"canonical_sha256":"09e21f35dcf6c1f7315ef4c4cdfcd3aa98df8a6905b1b378e4023dc7d9acf8f6","source":{"kind":"arxiv","id":"1504.06650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.06650","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1504.06650v1","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06650","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"BHRB6NO463A7","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BHRB6NO463A7OMK6","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BHRB6NO4","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:BHRB6NO463A7OMK66TCM37GTVK","target":"record","payload":{"canonical_record":{"source":{"id":"1504.06650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T21:43:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f4e45ce5b5f454a08d1f98301117af4b3445b270f9ca9c2ca4c66208c314098e","abstract_canon_sha256":"ca5b374f0ebf1313845253a279896ee9ced4c97151f25bc6d667e9fa4e95029d"},"schema_version":"1.0"},"canonical_sha256":"09e21f35dcf6c1f7315ef4c4cdfcd3aa98df8a6905b1b378e4023dc7d9acf8f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:52.884047Z","signature_b64":"ct8gfvJ+kSZoonUAn2Q9s4NidwA7GeuN8bRAY4+B33VDeND9U181tjd6eBf1BAyPHuTdS6l1YyGTeZqp836FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09e21f35dcf6c1f7315ef4c4cdfcd3aa98df8a6905b1b378e4023dc7d9acf8f6","last_reissued_at":"2026-05-18T02:17:52.883432Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:52.883432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.06650","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":"2026-05-18T02:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rORd/T8hE1VPHCmbXdR+Nb8gFQYu9VwiS560QPU2PpytdpXtrRMjPTshx61Yi7WK4mpkmoja0T6r9RiNtl/+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T13:10:11.587834Z"},"content_sha256":"1140d96db4b083bc95b958d815b999cf41dc8728791665731098cc8e2d48b8f1","schema_version":"1.0","event_id":"sha256:1140d96db4b083bc95b958d815b999cf41dc8728791665731098cc8e2d48b8f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:BHRB6NO463A7OMK66TCM37GTVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Dictionaries for Named Entity Recognition using Minimal Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Arvind Neelakantan, Michael Collins","submitted_at":"2015-04-24T21:43:55Z","abstract_excerpt":"This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples. We use Canonical Correlation Analysis (CCA) to obtain lower dimensional embeddings (representations) for candidate phrases and classify these phrases using a small number of labeled examples. Our method achieves 16.5% and 11.3% F-1 score improvement over co-training on disease and virus NER respectively. We also show that by adding candidate phrase embeddings as features in a sequence tagger gives better performance compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06650","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":"2026-05-18T02:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tLawWVnqK2O6E5w6FwMXyP8YX9tm9ZyWGvTdaWe4+guZi3XK3Df5/B1agUXqcUsFev0EfsU98nUFGlZsSoawBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T13:10:11.588173Z"},"content_sha256":"13307923c7891698244fad26a51df714ed9ecffa8ed8cf65fdb208c774796275","schema_version":"1.0","event_id":"sha256:13307923c7891698244fad26a51df714ed9ecffa8ed8cf65fdb208c774796275"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/bundle.json","state_url":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BHRB6NO463A7OMK66TCM37GTVK/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":"2026-07-04T13:10:11Z","links":{"resolver":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK","bundle":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/bundle.json","state":"https://pith.science/pith/BHRB6NO463A7OMK66TCM37GTVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BHRB6NO463A7OMK66TCM37GTVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:BHRB6NO463A7OMK66TCM37GTVK","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":"ca5b374f0ebf1313845253a279896ee9ced4c97151f25bc6d667e9fa4e95029d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T21:43:55Z","title_canon_sha256":"f4e45ce5b5f454a08d1f98301117af4b3445b270f9ca9c2ca4c66208c314098e"},"schema_version":"1.0","source":{"id":"1504.06650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.06650","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1504.06650v1","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06650","created_at":"2026-05-18T02:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"BHRB6NO463A7","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BHRB6NO463A7OMK6","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BHRB6NO4","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:13307923c7891698244fad26a51df714ed9ecffa8ed8cf65fdb208c774796275","target":"graph","created_at":"2026-05-18T02:17:52Z","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":"This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples. We use Canonical Correlation Analysis (CCA) to obtain lower dimensional embeddings (representations) for candidate phrases and classify these phrases using a small number of labeled examples. Our method achieves 16.5% and 11.3% F-1 score improvement over co-training on disease and virus NER respectively. We also show that by adding candidate phrase embeddings as features in a sequence tagger gives better performance compar","authors_text":"Arvind Neelakantan, Michael Collins","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T21:43:55Z","title":"Learning Dictionaries for Named Entity Recognition using Minimal Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06650","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":"sha256:1140d96db4b083bc95b958d815b999cf41dc8728791665731098cc8e2d48b8f1","target":"record","created_at":"2026-05-18T02:17:52Z","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":"ca5b374f0ebf1313845253a279896ee9ced4c97151f25bc6d667e9fa4e95029d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-04-24T21:43:55Z","title_canon_sha256":"f4e45ce5b5f454a08d1f98301117af4b3445b270f9ca9c2ca4c66208c314098e"},"schema_version":"1.0","source":{"id":"1504.06650","kind":"arxiv","version":1}},"canonical_sha256":"09e21f35dcf6c1f7315ef4c4cdfcd3aa98df8a6905b1b378e4023dc7d9acf8f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09e21f35dcf6c1f7315ef4c4cdfcd3aa98df8a6905b1b378e4023dc7d9acf8f6","first_computed_at":"2026-05-18T02:17:52.883432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:17:52.883432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ct8gfvJ+kSZoonUAn2Q9s4NidwA7GeuN8bRAY4+B33VDeND9U181tjd6eBf1BAyPHuTdS6l1YyGTeZqp836FDg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:17:52.884047Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.06650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1140d96db4b083bc95b958d815b999cf41dc8728791665731098cc8e2d48b8f1","sha256:13307923c7891698244fad26a51df714ed9ecffa8ed8cf65fdb208c774796275"],"state_sha256":"5cb2819d5f6c2f47e5d4fa3f76aed80058ba8e072d5fb2b20358a0b9d8adadc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v35VXAMlW4HUk/T01XxfgtUfDHINfeXmFippEcFPeUlNAJDKAspT+afqMtQTb4RKnXKaV155UTtVhdRYX75lAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T13:10:11.590010Z","bundle_sha256":"e4418887bec0d35e978b49eb82cea5aed0f570335b09b5245e91b782a83867a9"}}