{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:O6FK3U6UZY6EUD3WRUFOTCAJGD","short_pith_number":"pith:O6FK3U6U","canonical_record":{"source":{"id":"1507.07998","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-07-29T01:04:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"85c77abe468d7228c9da07afde110446da2d8cd8d191f7a8cdf7dfd64ee5bdbd","abstract_canon_sha256":"ce229445d8e45228e55344d24073fae6e95d65e1566a2ffa9d1ac159bd39e656"},"schema_version":"1.0"},"canonical_sha256":"778aadd3d4ce3c4a0f768d0ae9880930e44632cf37499e950c5e1f760e73d496","source":{"kind":"arxiv","id":"1507.07998","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.07998","created_at":"2026-05-18T01:36:08Z"},{"alias_kind":"arxiv_version","alias_value":"1507.07998v1","created_at":"2026-05-18T01:36:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.07998","created_at":"2026-05-18T01:36:08Z"},{"alias_kind":"pith_short_12","alias_value":"O6FK3U6UZY6E","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"O6FK3U6UZY6EUD3W","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"O6FK3U6U","created_at":"2026-05-18T12:29:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:O6FK3U6UZY6EUD3WRUFOTCAJGD","target":"record","payload":{"canonical_record":{"source":{"id":"1507.07998","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-07-29T01:04:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"85c77abe468d7228c9da07afde110446da2d8cd8d191f7a8cdf7dfd64ee5bdbd","abstract_canon_sha256":"ce229445d8e45228e55344d24073fae6e95d65e1566a2ffa9d1ac159bd39e656"},"schema_version":"1.0"},"canonical_sha256":"778aadd3d4ce3c4a0f768d0ae9880930e44632cf37499e950c5e1f760e73d496","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:08.691650Z","signature_b64":"fcBCKUc3+YK3Et3oEyzRKCm/H33goLomOzulUeHjyf2sd95Y17sQeeGdY4CJUbTuwT5dJTsfBh03mBguLBLyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"778aadd3d4ce3c4a0f768d0ae9880930e44632cf37499e950c5e1f760e73d496","last_reissued_at":"2026-05-18T01:36:08.691031Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:08.691031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.07998","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":"2026-05-18T01:36:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCvLAmUiAOFuEHDrmGQWukxyW8/CdSwmb6FfX6JsJsQC41a9fZKAhyH/xdiiwD+qO3SlJx/rKrtZvW5waVDUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:53:14.486672Z"},"content_sha256":"a5e5917ce7e2b3e3a3d49094baf4169e3d143d70e630567f4b14a93972ed4cd1","schema_version":"1.0","event_id":"sha256:a5e5917ce7e2b3e3a3d49094baf4169e3d143d70e630567f4b14a93972ed4cd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:O6FK3U6UZY6EUD3WRUFOTCAJGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Document Embedding with Paragraph Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew M. Dai, Christopher Olah, Quoc V. Le","submitted_at":"2015-07-29T01:04:28Z","abstract_excerpt":"Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide a more thorough comparison of Paragraph Vectors to other document modelling algorithms such as Latent Dirichlet Allocation, and evaluate performance of the method as we vary the dimensionality of the le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.07998","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":"2026-05-18T01:36:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/gmulUKi57Lz37mmKSfcxINjgLsLvjDhnEimXo5+dHUx4KaKH/sICWCsZnpr6NfIG/lsFyjNBASdWcZuuPeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:53:14.487063Z"},"content_sha256":"c287a69a611849c107270d6798d94fd2c9ae19198a1bb2257b5188426977445b","schema_version":"1.0","event_id":"sha256:c287a69a611849c107270d6798d94fd2c9ae19198a1bb2257b5188426977445b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6FK3U6UZY6EUD3WRUFOTCAJGD/bundle.json","state_url":"https://pith.science/pith/O6FK3U6UZY6EUD3WRUFOTCAJGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6FK3U6UZY6EUD3WRUFOTCAJGD/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":"2026-05-30T13:53:14Z","links":{"resolver":"https://pith.science/pith/O6FK3U6UZY6EUD3WRUFOTCAJGD","bundle":"https://pith.science/pith/O6FK3U6UZY6EUD3WRUFOTCAJGD/bundle.json","state":"https://pith.science/pith/O6FK3U6UZY6EUD3WRUFOTCAJGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6FK3U6UZY6EUD3WRUFOTCAJGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:O6FK3U6UZY6EUD3WRUFOTCAJGD","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":"ce229445d8e45228e55344d24073fae6e95d65e1566a2ffa9d1ac159bd39e656","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-07-29T01:04:28Z","title_canon_sha256":"85c77abe468d7228c9da07afde110446da2d8cd8d191f7a8cdf7dfd64ee5bdbd"},"schema_version":"1.0","source":{"id":"1507.07998","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.07998","created_at":"2026-05-18T01:36:08Z"},{"alias_kind":"arxiv_version","alias_value":"1507.07998v1","created_at":"2026-05-18T01:36:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.07998","created_at":"2026-05-18T01:36:08Z"},{"alias_kind":"pith_short_12","alias_value":"O6FK3U6UZY6E","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"O6FK3U6UZY6EUD3W","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"O6FK3U6U","created_at":"2026-05-18T12:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:c287a69a611849c107270d6798d94fd2c9ae19198a1bb2257b5188426977445b","target":"graph","created_at":"2026-05-18T01:36:08Z","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":"Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide a more thorough comparison of Paragraph Vectors to other document modelling algorithms such as Latent Dirichlet Allocation, and evaluate performance of the method as we vary the dimensionality of the le","authors_text":"Andrew M. Dai, Christopher Olah, Quoc V. Le","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-07-29T01:04:28Z","title":"Document Embedding with Paragraph Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.07998","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:a5e5917ce7e2b3e3a3d49094baf4169e3d143d70e630567f4b14a93972ed4cd1","target":"record","created_at":"2026-05-18T01:36:08Z","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":"ce229445d8e45228e55344d24073fae6e95d65e1566a2ffa9d1ac159bd39e656","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-07-29T01:04:28Z","title_canon_sha256":"85c77abe468d7228c9da07afde110446da2d8cd8d191f7a8cdf7dfd64ee5bdbd"},"schema_version":"1.0","source":{"id":"1507.07998","kind":"arxiv","version":1}},"canonical_sha256":"778aadd3d4ce3c4a0f768d0ae9880930e44632cf37499e950c5e1f760e73d496","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"778aadd3d4ce3c4a0f768d0ae9880930e44632cf37499e950c5e1f760e73d496","first_computed_at":"2026-05-18T01:36:08.691031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:08.691031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fcBCKUc3+YK3Et3oEyzRKCm/H33goLomOzulUeHjyf2sd95Y17sQeeGdY4CJUbTuwT5dJTsfBh03mBguLBLyCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:08.691650Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.07998","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5e5917ce7e2b3e3a3d49094baf4169e3d143d70e630567f4b14a93972ed4cd1","sha256:c287a69a611849c107270d6798d94fd2c9ae19198a1bb2257b5188426977445b"],"state_sha256":"5affbc3b0503d2cb0047d9e6565d727db19194442d6f5cb2fa204136d8d4e58d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kgrC5ozZd9G4TanoqI2oWAx9KWrsDJcvr2QVzemu7TyM5Ff0qmOjq+mEzOBX9InD/OXE+9ZHgkpriEv/Hd5XBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:53:14.489556Z","bundle_sha256":"910718fb9bc631884e8e54a06253c07f7907c8f4ae06d97a92c1129974edee4f"}}