{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4VXBJZKSUW35VCUKE73L56AM72","short_pith_number":"pith:4VXBJZKS","schema_version":"1.0","canonical_sha256":"e56e14e552a5b7da8a8a27f6bef80cfebb488428417965553b885f2e1fd31950","source":{"kind":"arxiv","id":"2002.11402","version":2},"attestation_state":"computed","paper":{"title":"Detecting Potential Topics In News Using BERT, CRF and Wikipedia","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Swapnil Ashok Jadhav","submitted_at":"2020-02-26T10:48:53Z","abstract_excerpt":"For a news content distribution platform like Dailyhunt, Named Entity Recognition is a pivotal task for building better user recommendation and notification algorithms. Apart from identifying names, locations, organisations from the news for 13+ Indian languages and use them in algorithms, we also need to identify n-grams which do not necessarily fit in the definition of Named-Entity, yet they are important. For example, \"me too movement\", \"beef ban\", \"alwar mob lynching\". In this exercise, given an English language text, we are trying to detect case-less n-grams which convey important informa"},"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":"2002.11402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-26T10:48:53Z","cross_cats_sorted":[],"title_canon_sha256":"4fa580ca37cf1adf5142a008fbebbb9ec471645e046b4fb446729becc5fca1a4","abstract_canon_sha256":"f4eb7e06b958ba5d216f525dc345331e3175d7ef97a002bd7b9825388e3e0824"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:28.922792Z","signature_b64":"T7au/qI5AIXPJLIKRbL19tf1jQAPMFs5v/Qm7OrZKrZT4bjyLkYFe3VNaufMTP8ON8X9tYX9LKP+QFPo0WyvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56e14e552a5b7da8a8a27f6bef80cfebb488428417965553b885f2e1fd31950","last_reissued_at":"2026-07-05T00:44:28.922460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:28.922460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Potential Topics In News Using BERT, CRF and Wikipedia","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Swapnil Ashok Jadhav","submitted_at":"2020-02-26T10:48:53Z","abstract_excerpt":"For a news content distribution platform like Dailyhunt, Named Entity Recognition is a pivotal task for building better user recommendation and notification algorithms. Apart from identifying names, locations, organisations from the news for 13+ Indian languages and use them in algorithms, we also need to identify n-grams which do not necessarily fit in the definition of Named-Entity, yet they are important. For example, \"me too movement\", \"beef ban\", \"alwar mob lynching\". In this exercise, given an English language text, we are trying to detect case-less n-grams which convey important informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11402","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.11402/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":"2002.11402","created_at":"2026-07-05T00:44:28.922515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11402v2","created_at":"2026-07-05T00:44:28.922515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11402","created_at":"2026-07-05T00:44:28.922515+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VXBJZKSUW35","created_at":"2026-07-05T00:44:28.922515+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VXBJZKSUW35VCUK","created_at":"2026-07-05T00:44:28.922515+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VXBJZKS","created_at":"2026-07-05T00:44:28.922515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01754","citing_title":"Unraveling Media Perspectives: A Comprehensive Methodology Combining Large Language Models, Topic Modeling, Sentiment Analysis, and Ontology Learning to Analyse Media Bias","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72","json":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72.json","graph_json":"https://pith.science/api/pith-number/4VXBJZKSUW35VCUKE73L56AM72/graph.json","events_json":"https://pith.science/api/pith-number/4VXBJZKSUW35VCUKE73L56AM72/events.json","paper":"https://pith.science/paper/4VXBJZKS"},"agent_actions":{"view_html":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72","download_json":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72.json","view_paper":"https://pith.science/paper/4VXBJZKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11402&json=true","fetch_graph":"https://pith.science/api/pith-number/4VXBJZKSUW35VCUKE73L56AM72/graph.json","fetch_events":"https://pith.science/api/pith-number/4VXBJZKSUW35VCUKE73L56AM72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72/action/storage_attestation","attest_author":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72/action/author_attestation","sign_citation":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72/action/citation_signature","submit_replication":"https://pith.science/pith/4VXBJZKSUW35VCUKE73L56AM72/action/replication_record"}},"created_at":"2026-07-05T00:44:28.922515+00:00","updated_at":"2026-07-05T00:44:28.922515+00:00"}