{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:J5PACDJ3GLKLUHKXJT3MPLEYSB","short_pith_number":"pith:J5PACDJ3","canonical_record":{"source":{"id":"1806.04411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-06-12T09:33:23Z","cross_cats_sorted":[],"title_canon_sha256":"be788218dbb17e25aec917905f7e04ed9797ab8ed958195cca4c7b4ee16a303d","abstract_canon_sha256":"5c23b8d09134a29368d86c018974337969d6529e89c4a12f375aea343fe9fd04"},"schema_version":"1.0"},"canonical_sha256":"4f5e010d3b32d4ba1d574cf6c7ac98906a5960560f731c441210b33e29310578","source":{"kind":"arxiv","id":"1806.04411","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04411","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04411v2","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04411","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"J5PACDJ3GLKL","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"J5PACDJ3GLKLUHKX","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"J5PACDJ3","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:J5PACDJ3GLKLUHKXJT3MPLEYSB","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-06-12T09:33:23Z","cross_cats_sorted":[],"title_canon_sha256":"be788218dbb17e25aec917905f7e04ed9797ab8ed958195cca4c7b4ee16a303d","abstract_canon_sha256":"5c23b8d09134a29368d86c018974337969d6529e89c4a12f375aea343fe9fd04"},"schema_version":"1.0"},"canonical_sha256":"4f5e010d3b32d4ba1d574cf6c7ac98906a5960560f731c441210b33e29310578","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:21.161533Z","signature_b64":"BdW/DvH+vNBOy8l1QMw9tWYJjhJB5frTsoMMuqxp0x6omGnC/yeennLQ/tAdt3WLBJR+FX0B6Fn0whuMKXdoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f5e010d3b32d4ba1d574cf6c7ac98906a5960560f731c441210b33e29310578","last_reissued_at":"2026-05-18T00:13:21.160861Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:21.160861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04411","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5ZZY6SDxizPKwV4qWYFREjuy+LRQ1ObKvjWEAop9upEPMHD9K4O8fkPlkhVyzFRksa8gaZ9Jdh+CTBiCg4WAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:52:30.317926Z"},"content_sha256":"07a0d29c62f832c3d438d35319e41b32883f7321722f41f3dfcd56d6c34ef8c1","schema_version":"1.0","event_id":"sha256:07a0d29c62f832c3d438d35319e41b32883f7321722f41f3dfcd56d6c34ef8c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:J5PACDJ3GLKLUHKXJT3MPLEYSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Named Entity Recognition with Extremely Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"James Allan, John Foley, Sheikh Muhammad Sarwar","submitted_at":"2018-06-12T09:33:23Z","abstract_excerpt":"Traditional information retrieval treats named entity recognition as a pre-indexing corpus annotation task, allowing entity tags to be indexed and used during search. Named entity taggers themselves are typically trained on thousands or tens of thousands of examples labeled by humans.\n  However, there is a long tail of named entities classes, and for these cases, labeled data may be impossible to find or justify financially. We propose exploring named entity recognition as a search task, where the named entity class of interest is a query, and entities of that class are the relevant \"documents"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04411","kind":"arxiv","version":2},"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":"2026-05-18T00:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a2v74MCwCPgg9yecnZXakJuQgaRjLrWzNacjlkRfAZWrwK802Oms/Ol4jXA9qNzQUeBbUlQpPP/Wjx1KUnW4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:52:30.318270Z"},"content_sha256":"f638b46917fff36df479c6cbb14b1b62058425b8ce3f83b4683406a89ef37f72","schema_version":"1.0","event_id":"sha256:f638b46917fff36df479c6cbb14b1b62058425b8ce3f83b4683406a89ef37f72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5PACDJ3GLKLUHKXJT3MPLEYSB/bundle.json","state_url":"https://pith.science/pith/J5PACDJ3GLKLUHKXJT3MPLEYSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5PACDJ3GLKLUHKXJT3MPLEYSB/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":"2026-05-19T11:52:30Z","links":{"resolver":"https://pith.science/pith/J5PACDJ3GLKLUHKXJT3MPLEYSB","bundle":"https://pith.science/pith/J5PACDJ3GLKLUHKXJT3MPLEYSB/bundle.json","state":"https://pith.science/pith/J5PACDJ3GLKLUHKXJT3MPLEYSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5PACDJ3GLKLUHKXJT3MPLEYSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:J5PACDJ3GLKLUHKXJT3MPLEYSB","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":"5c23b8d09134a29368d86c018974337969d6529e89c4a12f375aea343fe9fd04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-06-12T09:33:23Z","title_canon_sha256":"be788218dbb17e25aec917905f7e04ed9797ab8ed958195cca4c7b4ee16a303d"},"schema_version":"1.0","source":{"id":"1806.04411","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04411","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04411v2","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04411","created_at":"2026-05-18T00:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"J5PACDJ3GLKL","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"J5PACDJ3GLKLUHKX","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"J5PACDJ3","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:f638b46917fff36df479c6cbb14b1b62058425b8ce3f83b4683406a89ef37f72","target":"graph","created_at":"2026-05-18T00:13:21Z","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":"Traditional information retrieval treats named entity recognition as a pre-indexing corpus annotation task, allowing entity tags to be indexed and used during search. Named entity taggers themselves are typically trained on thousands or tens of thousands of examples labeled by humans.\n  However, there is a long tail of named entities classes, and for these cases, labeled data may be impossible to find or justify financially. We propose exploring named entity recognition as a search task, where the named entity class of interest is a query, and entities of that class are the relevant \"documents","authors_text":"James Allan, John Foley, Sheikh Muhammad Sarwar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-06-12T09:33:23Z","title":"Named Entity Recognition with Extremely Limited Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04411","kind":"arxiv","version":2},"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":"sha256:07a0d29c62f832c3d438d35319e41b32883f7321722f41f3dfcd56d6c34ef8c1","target":"record","created_at":"2026-05-18T00:13:21Z","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":"5c23b8d09134a29368d86c018974337969d6529e89c4a12f375aea343fe9fd04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-06-12T09:33:23Z","title_canon_sha256":"be788218dbb17e25aec917905f7e04ed9797ab8ed958195cca4c7b4ee16a303d"},"schema_version":"1.0","source":{"id":"1806.04411","kind":"arxiv","version":2}},"canonical_sha256":"4f5e010d3b32d4ba1d574cf6c7ac98906a5960560f731c441210b33e29310578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f5e010d3b32d4ba1d574cf6c7ac98906a5960560f731c441210b33e29310578","first_computed_at":"2026-05-18T00:13:21.160861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:21.160861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BdW/DvH+vNBOy8l1QMw9tWYJjhJB5frTsoMMuqxp0x6omGnC/yeennLQ/tAdt3WLBJR+FX0B6Fn0whuMKXdoCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:21.161533Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04411","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07a0d29c62f832c3d438d35319e41b32883f7321722f41f3dfcd56d6c34ef8c1","sha256:f638b46917fff36df479c6cbb14b1b62058425b8ce3f83b4683406a89ef37f72"],"state_sha256":"fab85f5c363fb551d1f984ff9b28ba4415db56aa664ace8caff5cde87b5454ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffhSZEWf5mOLOv7kXjM1QgU/YW/lqGvAOWX7jWthAntcdEH01ZTQrbviw48ms0oPQYNk5QI15ZgRHBDqZ9QVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T11:52:30.319850Z","bundle_sha256":"46e5435ff63f5702ce4582784b98f00457dda79a89a6eab5a1ecae69546d0cd3"}}