{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HF6UHI26EFFTOX3RAVDOTR5BJR","short_pith_number":"pith:HF6UHI26","schema_version":"1.0","canonical_sha256":"397d43a35e214b375f710546e9c7a14c48a6b1b9c77bffc5c2dd93b66bf56c58","source":{"kind":"arxiv","id":"1810.03947","version":4},"attestation_state":"computed","paper":{"title":"textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Florian Buettner, Hinrich Sch\\\"utze, Pankaj Gupta, Yatin Chaudhary","submitted_at":"2018-10-09T13:04:25Z","abstract_excerpt":"We address two challenges of probabilistic topic modelling in order to better estimate the probability of a word in a given context, i.e., P(word|context): (1) No Language Structure in Context: Probabilistic topic models ignore word order by summarizing a given context as a \"bag-of-word\" and consequently the semantics of words in the context is lost. The LSTM-LM learns a vector-space representation of each word by accounting for word order in local collocation patterns and models complex characteristics of language (e.g., syntax and semantics), while the TM simultaneously learns a latent repre"},"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":"1810.03947","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-09T13:04:25Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"f716d8e56c8706ebc9bc12bca60f04a9c7b3f7f79c83f9ec2a01c1e2894ddcda","abstract_canon_sha256":"4fd188a0d256ae5672f2b9888620fa6913a546552daeec42467ef456cbfe7dbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:51.965339Z","signature_b64":"Bx1joBUZOEpPExbcOomxPdaUVaWySCMQSyenciSDiEGo+kF2/vdulb6LGdPtpHuqx78pJjrFOIpuaUSfs4jgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"397d43a35e214b375f710546e9c7a14c48a6b1b9c77bffc5c2dd93b66bf56c58","last_reissued_at":"2026-05-17T23:52:51.964582Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:51.964582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Florian Buettner, Hinrich Sch\\\"utze, Pankaj Gupta, Yatin Chaudhary","submitted_at":"2018-10-09T13:04:25Z","abstract_excerpt":"We address two challenges of probabilistic topic modelling in order to better estimate the probability of a word in a given context, i.e., P(word|context): (1) No Language Structure in Context: Probabilistic topic models ignore word order by summarizing a given context as a \"bag-of-word\" and consequently the semantics of words in the context is lost. The LSTM-LM learns a vector-space representation of each word by accounting for word order in local collocation patterns and models complex characteristics of language (e.g., syntax and semantics), while the TM simultaneously learns a latent repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03947","kind":"arxiv","version":4},"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":"1810.03947","created_at":"2026-05-17T23:52:51.964685+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03947v4","created_at":"2026-05-17T23:52:51.964685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03947","created_at":"2026-05-17T23:52:51.964685+00:00"},{"alias_kind":"pith_short_12","alias_value":"HF6UHI26EFFT","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HF6UHI26EFFTOX3R","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HF6UHI26","created_at":"2026-05-18T12:32:28.185984+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/HF6UHI26EFFTOX3RAVDOTR5BJR","json":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR.json","graph_json":"https://pith.science/api/pith-number/HF6UHI26EFFTOX3RAVDOTR5BJR/graph.json","events_json":"https://pith.science/api/pith-number/HF6UHI26EFFTOX3RAVDOTR5BJR/events.json","paper":"https://pith.science/paper/HF6UHI26"},"agent_actions":{"view_html":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR","download_json":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR.json","view_paper":"https://pith.science/paper/HF6UHI26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03947&json=true","fetch_graph":"https://pith.science/api/pith-number/HF6UHI26EFFTOX3RAVDOTR5BJR/graph.json","fetch_events":"https://pith.science/api/pith-number/HF6UHI26EFFTOX3RAVDOTR5BJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR/action/storage_attestation","attest_author":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR/action/author_attestation","sign_citation":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR/action/citation_signature","submit_replication":"https://pith.science/pith/HF6UHI26EFFTOX3RAVDOTR5BJR/action/replication_record"}},"created_at":"2026-05-17T23:52:51.964685+00:00","updated_at":"2026-05-17T23:52:51.964685+00:00"}