{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4VXBJZKSUW35VCUKE73L56AM72","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":"f4eb7e06b958ba5d216f525dc345331e3175d7ef97a002bd7b9825388e3e0824","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-26T10:48:53Z","title_canon_sha256":"4fa580ca37cf1adf5142a008fbebbb9ec471645e046b4fb446729becc5fca1a4"},"schema_version":"1.0","source":{"id":"2002.11402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11402","created_at":"2026-07-05T00:44:28Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11402v2","created_at":"2026-07-05T00:44:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11402","created_at":"2026-07-05T00:44:28Z"},{"alias_kind":"pith_short_12","alias_value":"4VXBJZKSUW35","created_at":"2026-07-05T00:44:28Z"},{"alias_kind":"pith_short_16","alias_value":"4VXBJZKSUW35VCUK","created_at":"2026-07-05T00:44:28Z"},{"alias_kind":"pith_short_8","alias_value":"4VXBJZKS","created_at":"2026-07-05T00:44:28Z"}],"graph_snapshots":[{"event_id":"sha256:d978bb81856b63596647dab7cb6aa3499ec5d7b93e183a6da44f7a4062ccec94","target":"graph","created_at":"2026-07-05T00:44:28Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.11402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Swapnil Ashok Jadhav","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-26T10:48:53Z","title":"Detecting Potential Topics In News Using BERT, CRF and Wikipedia"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11402","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":"sha256:09f87078267e6db03951d1a887b9838de264209c50301d9ba82cb0d9d2fadef8","target":"record","created_at":"2026-07-05T00:44:28Z","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":"f4eb7e06b958ba5d216f525dc345331e3175d7ef97a002bd7b9825388e3e0824","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-26T10:48:53Z","title_canon_sha256":"4fa580ca37cf1adf5142a008fbebbb9ec471645e046b4fb446729becc5fca1a4"},"schema_version":"1.0","source":{"id":"2002.11402","kind":"arxiv","version":2}},"canonical_sha256":"e56e14e552a5b7da8a8a27f6bef80cfebb488428417965553b885f2e1fd31950","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e56e14e552a5b7da8a8a27f6bef80cfebb488428417965553b885f2e1fd31950","first_computed_at":"2026-07-05T00:44:28.922460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:28.922460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T7au/qI5AIXPJLIKRbL19tf1jQAPMFs5v/Qm7OrZKrZT4bjyLkYFe3VNaufMTP8ON8X9tYX9LKP+QFPo0WyvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:28.922792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09f87078267e6db03951d1a887b9838de264209c50301d9ba82cb0d9d2fadef8","sha256:d978bb81856b63596647dab7cb6aa3499ec5d7b93e183a6da44f7a4062ccec94"],"state_sha256":"2541dc8db2ccd7321d6b80e2cf96fdbe99266cef591ac87b10d512d472d53d60"}