{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VZXHDRLMC3XCYCHMEQ67NSZJAF","short_pith_number":"pith:VZXHDRLM","canonical_record":{"source":{"id":"1801.04813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-15T14:11:57Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0b55ce873f59a343b85ba4ded3657f9b702ac3711ea311baf902d75c93ad020a","abstract_canon_sha256":"11cee22027de56f54b468ef64e837b478564160e0443f86ad0d37af0fc8c64cd"},"schema_version":"1.0"},"canonical_sha256":"ae6e71c56c16ee2c08ec243df6cb290159f1cbab1aad8427fd094b0d42e71202","source":{"kind":"arxiv","id":"1801.04813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04813","created_at":"2026-05-18T00:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04813v1","created_at":"2026-05-18T00:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04813","created_at":"2026-05-18T00:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"VZXHDRLMC3XC","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VZXHDRLMC3XCYCHM","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VZXHDRLM","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VZXHDRLMC3XCYCHMEQ67NSZJAF","target":"record","payload":{"canonical_record":{"source":{"id":"1801.04813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-15T14:11:57Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0b55ce873f59a343b85ba4ded3657f9b702ac3711ea311baf902d75c93ad020a","abstract_canon_sha256":"11cee22027de56f54b468ef64e837b478564160e0443f86ad0d37af0fc8c64cd"},"schema_version":"1.0"},"canonical_sha256":"ae6e71c56c16ee2c08ec243df6cb290159f1cbab1aad8427fd094b0d42e71202","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:03.179802Z","signature_b64":"gah+I+3bW48mtYdUcl9eJKT9WiEo8VvttIQyOsw5Zvhp0UWF572rvac6pWFQtmcJ606sR6giaJ/vxOwaTQeMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae6e71c56c16ee2c08ec243df6cb290159f1cbab1aad8427fd094b0d42e71202","last_reissued_at":"2026-05-18T00:26:03.179104Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:03.179104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.04813","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":"2026-05-18T00:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BSISsY8JseYkhAEhrEOiJybqRCr6wvJnNtbahGFUtRyE616hZYeXTqoGwpAG1msP5xmYBnyEWuPSbpex9t6hDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:48:57.754085Z"},"content_sha256":"70fdeb408b27b356b5a8d64f51e30f8f125c2b89331be7703c76c4d3e9f0a1dc","schema_version":"1.0","event_id":"sha256:70fdeb408b27b356b5a8d64f51e30f8f125c2b89331be7703c76c4d3e9f0a1dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VZXHDRLMC3XCYCHMEQ67NSZJAF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predicting Movie Genres Based on Plot Summaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Quan Hoang","submitted_at":"2018-01-15T14:11:57Z","abstract_excerpt":"This project explores several Machine Learning methods to predict movie genres based on plot summaries. Naive Bayes, Word2Vec+XGBoost and Recurrent Neural Networks are used for text classification, while K-binary transformation, rank method and probabilistic classification with learned probability threshold are employed for the multi-label problem involved in the genre tagging task.Experiments with more than 250,000 movies show that employing the Gated Recurrent Units (GRU) neural networks for the probabilistic classification with learned probability threshold approach achieves the best result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04813","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":"2026-05-18T00:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c72cAGstEGnZ2koB22dmzXgJ4wCwJ4crcYLGicP9064R3TwW2KMKnvbeD/9NZ0YZ+wy8FgpqWrYtgGA/6q9mBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:48:57.754760Z"},"content_sha256":"1987a4680410cb33d66135add8a724ebd951ef26c79623d28519f0b048c1faa6","schema_version":"1.0","event_id":"sha256:1987a4680410cb33d66135add8a724ebd951ef26c79623d28519f0b048c1faa6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZXHDRLMC3XCYCHMEQ67NSZJAF/bundle.json","state_url":"https://pith.science/pith/VZXHDRLMC3XCYCHMEQ67NSZJAF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZXHDRLMC3XCYCHMEQ67NSZJAF/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":"2026-06-05T18:48:57Z","links":{"resolver":"https://pith.science/pith/VZXHDRLMC3XCYCHMEQ67NSZJAF","bundle":"https://pith.science/pith/VZXHDRLMC3XCYCHMEQ67NSZJAF/bundle.json","state":"https://pith.science/pith/VZXHDRLMC3XCYCHMEQ67NSZJAF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZXHDRLMC3XCYCHMEQ67NSZJAF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VZXHDRLMC3XCYCHMEQ67NSZJAF","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":"11cee22027de56f54b468ef64e837b478564160e0443f86ad0d37af0fc8c64cd","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-15T14:11:57Z","title_canon_sha256":"0b55ce873f59a343b85ba4ded3657f9b702ac3711ea311baf902d75c93ad020a"},"schema_version":"1.0","source":{"id":"1801.04813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04813","created_at":"2026-05-18T00:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04813v1","created_at":"2026-05-18T00:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04813","created_at":"2026-05-18T00:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"VZXHDRLMC3XC","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VZXHDRLMC3XCYCHM","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VZXHDRLM","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:1987a4680410cb33d66135add8a724ebd951ef26c79623d28519f0b048c1faa6","target":"graph","created_at":"2026-05-18T00:26:03Z","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":"This project explores several Machine Learning methods to predict movie genres based on plot summaries. Naive Bayes, Word2Vec+XGBoost and Recurrent Neural Networks are used for text classification, while K-binary transformation, rank method and probabilistic classification with learned probability threshold are employed for the multi-label problem involved in the genre tagging task.Experiments with more than 250,000 movies show that employing the Gated Recurrent Units (GRU) neural networks for the probabilistic classification with learned probability threshold approach achieves the best result","authors_text":"Quan Hoang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-15T14:11:57Z","title":"Predicting Movie Genres Based on Plot Summaries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04813","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":"sha256:70fdeb408b27b356b5a8d64f51e30f8f125c2b89331be7703c76c4d3e9f0a1dc","target":"record","created_at":"2026-05-18T00:26:03Z","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":"11cee22027de56f54b468ef64e837b478564160e0443f86ad0d37af0fc8c64cd","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-15T14:11:57Z","title_canon_sha256":"0b55ce873f59a343b85ba4ded3657f9b702ac3711ea311baf902d75c93ad020a"},"schema_version":"1.0","source":{"id":"1801.04813","kind":"arxiv","version":1}},"canonical_sha256":"ae6e71c56c16ee2c08ec243df6cb290159f1cbab1aad8427fd094b0d42e71202","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae6e71c56c16ee2c08ec243df6cb290159f1cbab1aad8427fd094b0d42e71202","first_computed_at":"2026-05-18T00:26:03.179104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:03.179104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gah+I+3bW48mtYdUcl9eJKT9WiEo8VvttIQyOsw5Zvhp0UWF572rvac6pWFQtmcJ606sR6giaJ/vxOwaTQeMAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:03.179802Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.04813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70fdeb408b27b356b5a8d64f51e30f8f125c2b89331be7703c76c4d3e9f0a1dc","sha256:1987a4680410cb33d66135add8a724ebd951ef26c79623d28519f0b048c1faa6"],"state_sha256":"7cc878690141e95a644d2350736651a723607ec4f5292f4d59988ca474b38edc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+CXjenIn4gM5dfJYUbCzuW5w2cdQRr+SodcX3btRkxapr8hxRLJwmHfVS5WchmRFBPp8DSPV0J+7ELQX0v+8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T18:48:57.758032Z","bundle_sha256":"de27caae71adcd64baf21908d210293a26a023ecf7289086e0a3ddde35a573bf"}}