{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VT5NOMLO2CKGZSS23WJSWNNZH6","short_pith_number":"pith:VT5NOMLO","schema_version":"1.0","canonical_sha256":"acfad7316ed0946cca5add932b35b93fbf343c436f801e488fd81eaa3bcc2e61","source":{"kind":"arxiv","id":"1707.02377","version":1},"attestation_state":"computed","paper":{"title":"Efficient Vector Representation for Documents through Corruption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Minmin Chen","submitted_at":"2017-07-08T00:57:01Z","abstract_excerpt":"We present an efficient document representation learning framework, Document Vector through Corruption (Doc2VecC). Doc2VecC represents each document as a simple average of word embeddings. It ensures a representation generated as such captures the semantic meanings of the document during learning. A corruption model is included, which introduces a data-dependent regularization that favors informative or rare words while forcing the embeddings of common and non-discriminative ones to be close to zero. Doc2VecC produces significantly better word embeddings than Word2Vec. We compare Doc2VecC with"},"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":"1707.02377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T00:57:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cd62b20b4422a0f9811406c18eda2f4299d2de691644b3351e001db62dac1dbe","abstract_canon_sha256":"07ca5d62e3aa0dc4ceb29e09d0bb57210d728dcca859f07eff2b6ea10144fd8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:39.360678Z","signature_b64":"XMVnq47c2zwyM9AxosAvV3zNY/YLNNGmypRnvnpAV5sqIWx/tgqm6O7iKLUxjvhbpPWJoJDzzf/cdF1JzteoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acfad7316ed0946cca5add932b35b93fbf343c436f801e488fd81eaa3bcc2e61","last_reissued_at":"2026-05-18T00:40:39.359914Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:39.359914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Vector Representation for Documents through Corruption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Minmin Chen","submitted_at":"2017-07-08T00:57:01Z","abstract_excerpt":"We present an efficient document representation learning framework, Document Vector through Corruption (Doc2VecC). Doc2VecC represents each document as a simple average of word embeddings. It ensures a representation generated as such captures the semantic meanings of the document during learning. A corruption model is included, which introduces a data-dependent regularization that favors informative or rare words while forcing the embeddings of common and non-discriminative ones to be close to zero. Doc2VecC produces significantly better word embeddings than Word2Vec. We compare Doc2VecC with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02377","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":"1707.02377","created_at":"2026-05-18T00:40:39.360047+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.02377v1","created_at":"2026-05-18T00:40:39.360047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02377","created_at":"2026-05-18T00:40:39.360047+00:00"},{"alias_kind":"pith_short_12","alias_value":"VT5NOMLO2CKG","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VT5NOMLO2CKGZSS2","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VT5NOMLO","created_at":"2026-05-18T12:31:49.984773+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/VT5NOMLO2CKGZSS23WJSWNNZH6","json":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6.json","graph_json":"https://pith.science/api/pith-number/VT5NOMLO2CKGZSS23WJSWNNZH6/graph.json","events_json":"https://pith.science/api/pith-number/VT5NOMLO2CKGZSS23WJSWNNZH6/events.json","paper":"https://pith.science/paper/VT5NOMLO"},"agent_actions":{"view_html":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6","download_json":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6.json","view_paper":"https://pith.science/paper/VT5NOMLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.02377&json=true","fetch_graph":"https://pith.science/api/pith-number/VT5NOMLO2CKGZSS23WJSWNNZH6/graph.json","fetch_events":"https://pith.science/api/pith-number/VT5NOMLO2CKGZSS23WJSWNNZH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/action/storage_attestation","attest_author":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/action/author_attestation","sign_citation":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/action/citation_signature","submit_replication":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/action/replication_record"}},"created_at":"2026-05-18T00:40:39.360047+00:00","updated_at":"2026-05-18T00:40:39.360047+00:00"}