{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:42FD23HYZES7R5APFFQKGYWJI5","short_pith_number":"pith:42FD23HY","canonical_record":{"source":{"id":"1803.01465","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-05T02:44:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63e2be135f6dabe67e8e3a908bec53c5ba3f4720ed785f4e67ed7a3015c57b10","abstract_canon_sha256":"9fd52356dc50356be735642f0c2f0096708ddbd6eff8f188a71c5a17d25a64a2"},"schema_version":"1.0"},"canonical_sha256":"e68a3d6cf8c925f8f40f2960a362c9476ccfebe3195460b91d70fb977b97f786","source":{"kind":"arxiv","id":"1803.01465","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01465","created_at":"2026-05-18T00:19:46Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01465v3","created_at":"2026-05-18T00:19:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01465","created_at":"2026-05-18T00:19:46Z"},{"alias_kind":"pith_short_12","alias_value":"42FD23HYZES7","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"42FD23HYZES7R5AP","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"42FD23HY","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:42FD23HYZES7R5APFFQKGYWJI5","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01465","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-05T02:44:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63e2be135f6dabe67e8e3a908bec53c5ba3f4720ed785f4e67ed7a3015c57b10","abstract_canon_sha256":"9fd52356dc50356be735642f0c2f0096708ddbd6eff8f188a71c5a17d25a64a2"},"schema_version":"1.0"},"canonical_sha256":"e68a3d6cf8c925f8f40f2960a362c9476ccfebe3195460b91d70fb977b97f786","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:46.966606Z","signature_b64":"OGmk7zuqMW2GU4Ipt7ynxk33aODr0SjFaYyAneTsj0TCb8tYo0I0PKG3pODYBqgK1KujjcSlfnXYRFnvhWRHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e68a3d6cf8c925f8f40f2960a362c9476ccfebe3195460b91d70fb977b97f786","last_reissued_at":"2026-05-18T00:19:46.965763Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:46.965763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01465","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PNiqcJKRNT8753rtvmOhyARDPme/5tIPkmPxIHDAPoLddUSxka8sWlBg8cH5ZmWwjehFOL18J78nReRBl6zoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:12:43.993906Z"},"content_sha256":"fed157933ea73ed988bdb065b3f10d0557979e5d9792eebdf067d0458c4bb230","schema_version":"1.0","event_id":"sha256:fed157933ea73ed988bdb065b3f10d0557979e5d9792eebdf067d0458c4bb230"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:42FD23HYZES7R5APFFQKGYWJI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shuming Ma, Sujian Li, Wei Li, Wenjie Li, Xuancheng Ren, Xu Sun","submitted_at":"2018-03-05T02:44:42Z","abstract_excerpt":"Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words. Therefore, the generated sentences are often grammatically correct but semantically improper. In this work, we introduce a novel model based on the encoder-decoder framework, called Word Embedding Attention Network (WEAN). Our proposed model generates the words by querying distributed word representations (i.e. neural word embeddings), hoping to capturing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01465","kind":"arxiv","version":3},"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":"2026-05-18T00:19:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S35a4Lv6psI3hDZXf0RoyctmqvQWC8GQ5OVZe2Dk4wZLXuH/X+VdFPTBvtrhMfn6ayQCqrW01ZfEhPQVPlLgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:12:43.994250Z"},"content_sha256":"0f64756258b1c2a0f9a07ccd5f8a1245376ff87babc7503d512c7bde3d87e33e","schema_version":"1.0","event_id":"sha256:0f64756258b1c2a0f9a07ccd5f8a1245376ff87babc7503d512c7bde3d87e33e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/42FD23HYZES7R5APFFQKGYWJI5/bundle.json","state_url":"https://pith.science/pith/42FD23HYZES7R5APFFQKGYWJI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/42FD23HYZES7R5APFFQKGYWJI5/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":"2026-06-02T07:12:43Z","links":{"resolver":"https://pith.science/pith/42FD23HYZES7R5APFFQKGYWJI5","bundle":"https://pith.science/pith/42FD23HYZES7R5APFFQKGYWJI5/bundle.json","state":"https://pith.science/pith/42FD23HYZES7R5APFFQKGYWJI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/42FD23HYZES7R5APFFQKGYWJI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:42FD23HYZES7R5APFFQKGYWJI5","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":"9fd52356dc50356be735642f0c2f0096708ddbd6eff8f188a71c5a17d25a64a2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-05T02:44:42Z","title_canon_sha256":"63e2be135f6dabe67e8e3a908bec53c5ba3f4720ed785f4e67ed7a3015c57b10"},"schema_version":"1.0","source":{"id":"1803.01465","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01465","created_at":"2026-05-18T00:19:46Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01465v3","created_at":"2026-05-18T00:19:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01465","created_at":"2026-05-18T00:19:46Z"},{"alias_kind":"pith_short_12","alias_value":"42FD23HYZES7","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"42FD23HYZES7R5AP","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"42FD23HY","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:0f64756258b1c2a0f9a07ccd5f8a1245376ff87babc7503d512c7bde3d87e33e","target":"graph","created_at":"2026-05-18T00:19:46Z","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":"Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words. Therefore, the generated sentences are often grammatically correct but semantically improper. In this work, we introduce a novel model based on the encoder-decoder framework, called Word Embedding Attention Network (WEAN). Our proposed model generates the words by querying distributed word representations (i.e. neural word embeddings), hoping to capturing th","authors_text":"Shuming Ma, Sujian Li, Wei Li, Wenjie Li, Xuancheng Ren, Xu Sun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-05T02:44:42Z","title":"Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01465","kind":"arxiv","version":3},"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:fed157933ea73ed988bdb065b3f10d0557979e5d9792eebdf067d0458c4bb230","target":"record","created_at":"2026-05-18T00:19:46Z","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":"9fd52356dc50356be735642f0c2f0096708ddbd6eff8f188a71c5a17d25a64a2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-05T02:44:42Z","title_canon_sha256":"63e2be135f6dabe67e8e3a908bec53c5ba3f4720ed785f4e67ed7a3015c57b10"},"schema_version":"1.0","source":{"id":"1803.01465","kind":"arxiv","version":3}},"canonical_sha256":"e68a3d6cf8c925f8f40f2960a362c9476ccfebe3195460b91d70fb977b97f786","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e68a3d6cf8c925f8f40f2960a362c9476ccfebe3195460b91d70fb977b97f786","first_computed_at":"2026-05-18T00:19:46.965763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:46.965763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OGmk7zuqMW2GU4Ipt7ynxk33aODr0SjFaYyAneTsj0TCb8tYo0I0PKG3pODYBqgK1KujjcSlfnXYRFnvhWRHAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:46.966606Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01465","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fed157933ea73ed988bdb065b3f10d0557979e5d9792eebdf067d0458c4bb230","sha256:0f64756258b1c2a0f9a07ccd5f8a1245376ff87babc7503d512c7bde3d87e33e"],"state_sha256":"92a4a8b74b3410c19403f45c3d59b811c0c085839e7d802345f7917956650d81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71VX8L0heB3sRk7x2T42bQhrCkGXZTdhaO+7Gvxt/7Jb+OL30dM8DDF1r3qZQUIc+kFk8WkSmxK4HRLQG/YeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T07:12:43.996214Z","bundle_sha256":"494b191b680f16ea0358506aab07cb3c3558a0efaeff2c9481a8bf43a7717c7a"}}