{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VT5NOMLO2CKGZSS23WJSWNNZH6","short_pith_number":"pith:VT5NOMLO","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"},"canonical_sha256":"acfad7316ed0946cca5add932b35b93fbf343c436f801e488fd81eaa3bcc2e61","source":{"kind":"arxiv","id":"1707.02377","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02377","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02377v1","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02377","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"pith_short_12","alias_value":"VT5NOMLO2CKG","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VT5NOMLO2CKGZSS2","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VT5NOMLO","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VT5NOMLO2CKGZSS23WJSWNNZH6","target":"record","payload":{"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"},"canonical_sha256":"acfad7316ed0946cca5add932b35b93fbf343c436f801e488fd81eaa3bcc2e61","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"},"source_kind":"arxiv","source_id":"1707.02377","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:40:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uwbstEMKkpPcuYu3PGu52rClgjVvCvp+88Sf7Qf85+DAKWd7ZNyZjlSqgg8+g93SJyFuDj4BmU4jCB5ywHLjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:08:28.149971Z"},"content_sha256":"a34b5e487f9f0b29b206bc930ab45bb5237e255152c786ac94e5c024fd964b7f","schema_version":"1.0","event_id":"sha256:a34b5e487f9f0b29b206bc930ab45bb5237e255152c786ac94e5c024fd964b7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VT5NOMLO2CKGZSS23WJSWNNZH6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:40:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JN8aOXedcFlabZ7i1dtHXTKeviAGyJc33qGv9y8HXghu+YlqzqCcoq+RrMA1OgFX84KH+h+PNfrWpQZtpvqZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:08:28.150686Z"},"content_sha256":"5e09856bb19e6ca65fca274cf7153a8c16d1b1efc1336f2b4abd3f9a55794359","schema_version":"1.0","event_id":"sha256:5e09856bb19e6ca65fca274cf7153a8c16d1b1efc1336f2b4abd3f9a55794359"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/bundle.json","state_url":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T23:08:28Z","links":{"resolver":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6","bundle":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/bundle.json","state":"https://pith.science/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VT5NOMLO2CKGZSS23WJSWNNZH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VT5NOMLO2CKGZSS23WJSWNNZH6","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":"07ca5d62e3aa0dc4ceb29e09d0bb57210d728dcca859f07eff2b6ea10144fd8e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T00:57:01Z","title_canon_sha256":"cd62b20b4422a0f9811406c18eda2f4299d2de691644b3351e001db62dac1dbe"},"schema_version":"1.0","source":{"id":"1707.02377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02377","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02377v1","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02377","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"pith_short_12","alias_value":"VT5NOMLO2CKG","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VT5NOMLO2CKGZSS2","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VT5NOMLO","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:5e09856bb19e6ca65fca274cf7153a8c16d1b1efc1336f2b4abd3f9a55794359","target":"graph","created_at":"2026-05-18T00:40:39Z","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"},"paper":{"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","authors_text":"Minmin Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T00:57:01Z","title":"Efficient Vector Representation for Documents through Corruption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02377","kind":"arxiv","version":1},"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:a34b5e487f9f0b29b206bc930ab45bb5237e255152c786ac94e5c024fd964b7f","target":"record","created_at":"2026-05-18T00:40:39Z","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":"07ca5d62e3aa0dc4ceb29e09d0bb57210d728dcca859f07eff2b6ea10144fd8e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-08T00:57:01Z","title_canon_sha256":"cd62b20b4422a0f9811406c18eda2f4299d2de691644b3351e001db62dac1dbe"},"schema_version":"1.0","source":{"id":"1707.02377","kind":"arxiv","version":1}},"canonical_sha256":"acfad7316ed0946cca5add932b35b93fbf343c436f801e488fd81eaa3bcc2e61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acfad7316ed0946cca5add932b35b93fbf343c436f801e488fd81eaa3bcc2e61","first_computed_at":"2026-05-18T00:40:39.359914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:39.359914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XMVnq47c2zwyM9AxosAvV3zNY/YLNNGmypRnvnpAV5sqIWx/tgqm6O7iKLUxjvhbpPWJoJDzzf/cdF1JzteoDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:39.360678Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.02377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a34b5e487f9f0b29b206bc930ab45bb5237e255152c786ac94e5c024fd964b7f","sha256:5e09856bb19e6ca65fca274cf7153a8c16d1b1efc1336f2b4abd3f9a55794359"],"state_sha256":"91b946f0cc29778fe8823d8ec6ef95caa58f81621c4960aea24c5582c6244d44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMSqgR5NAgBiIbGakScWTg5+HEVSPpNlDH/L0MHrpO3oh2wcJhjvrwiGrPCZf98n5Eb2UJIvqUZ9CZjGwm6yAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:08:28.154498Z","bundle_sha256":"4eeb08d0bfe09b4d0646391358f03f26cc3579cd76677e00cfadf7345670c85a"}}