{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DNIKWUUR4BEXNQLOQL2NANAWIQ","short_pith_number":"pith:DNIKWUUR","schema_version":"1.0","canonical_sha256":"1b50ab5291e04976c16e82f4d0341644352648a4a1ae49680dffd682a6aeec3a","source":{"kind":"arxiv","id":"1602.06979","version":1},"attestation_state":"computed","paper":{"title":"Empath: Understanding Topic Signals in Large-Scale Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Binbin Chen, Ethan Fast, Michael Bernstein","submitted_at":"2016-02-22T21:47:43Z","abstract_excerpt":"Human language is colored by a broad range of topics, but existing text analysis tools only focus on a small number of them. We present Empath, a tool that can generate and validate new lexical categories on demand from a small set of seed terms (like \"bleed\" and \"punch\" to generate the category violence). Empath draws connotations between words and phrases by deep learning a neural embedding across more than 1.8 billion words of modern fiction. Given a small set of seed words that characterize a category, Empath uses its neural embedding to discover new related terms, then validates the categ"},"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":"1602.06979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-22T21:47:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"157760bb65ebc3dce285f1db0f5b4bc3cd6c2bedfedc8646257bcb62b0f0ae07","abstract_canon_sha256":"b123bc796492bbd5e7ad2017973f3a69ac858c381738130f18f810c9615094f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:07.481381Z","signature_b64":"Koh6kECT+q6mHcYa8Cbql724sVtL6iTwiHCem8ITGoBOLUvPdbTjuZPGuCXwMl+v4rAz0Kw2LzNykOO2dqkyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b50ab5291e04976c16e82f4d0341644352648a4a1ae49680dffd682a6aeec3a","last_reissued_at":"2026-05-18T01:20:07.480709Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:07.480709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empath: Understanding Topic Signals in Large-Scale Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Binbin Chen, Ethan Fast, Michael Bernstein","submitted_at":"2016-02-22T21:47:43Z","abstract_excerpt":"Human language is colored by a broad range of topics, but existing text analysis tools only focus on a small number of them. We present Empath, a tool that can generate and validate new lexical categories on demand from a small set of seed terms (like \"bleed\" and \"punch\" to generate the category violence). Empath draws connotations between words and phrases by deep learning a neural embedding across more than 1.8 billion words of modern fiction. Given a small set of seed words that characterize a category, Empath uses its neural embedding to discover new related terms, then validates the categ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06979","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1602.06979","created_at":"2026-05-18T01:20:07.480801+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.06979v1","created_at":"2026-05-18T01:20:07.480801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06979","created_at":"2026-05-18T01:20:07.480801+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNIKWUUR4BEX","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNIKWUUR4BEXNQLO","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNIKWUUR","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ","json":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ.json","graph_json":"https://pith.science/api/pith-number/DNIKWUUR4BEXNQLOQL2NANAWIQ/graph.json","events_json":"https://pith.science/api/pith-number/DNIKWUUR4BEXNQLOQL2NANAWIQ/events.json","paper":"https://pith.science/paper/DNIKWUUR"},"agent_actions":{"view_html":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ","download_json":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ.json","view_paper":"https://pith.science/paper/DNIKWUUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.06979&json=true","fetch_graph":"https://pith.science/api/pith-number/DNIKWUUR4BEXNQLOQL2NANAWIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DNIKWUUR4BEXNQLOQL2NANAWIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ/action/storage_attestation","attest_author":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ/action/author_attestation","sign_citation":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ/action/citation_signature","submit_replication":"https://pith.science/pith/DNIKWUUR4BEXNQLOQL2NANAWIQ/action/replication_record"}},"created_at":"2026-05-18T01:20:07.480801+00:00","updated_at":"2026-05-18T01:20:07.480801+00:00"}