{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5GVYXNF6U2GEXINYWXCKLRKMYQ","short_pith_number":"pith:5GVYXNF6","canonical_record":{"source":{"id":"2005.01278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T05:20:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d1f04785e5f374e74cd587dc6a136c0f88ed5e1f78ff7209915a721b7281c82d","abstract_canon_sha256":"8103406fcbc8d217d14b532364706dcfc4c984891324e54bbf4a0115dbf88e03"},"schema_version":"1.0"},"canonical_sha256":"e9ab8bb4bea68c4ba1b8b5c4a5c54cc405ce197d45e2831cd2b1583dd1888af5","source":{"kind":"arxiv","id":"2005.01278","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01278","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01278v1","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01278","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"pith_short_12","alias_value":"5GVYXNF6U2GE","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"pith_short_16","alias_value":"5GVYXNF6U2GEXINY","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"pith_short_8","alias_value":"5GVYXNF6","created_at":"2026-07-05T01:00:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5GVYXNF6U2GEXINYWXCKLRKMYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2005.01278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T05:20:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d1f04785e5f374e74cd587dc6a136c0f88ed5e1f78ff7209915a721b7281c82d","abstract_canon_sha256":"8103406fcbc8d217d14b532364706dcfc4c984891324e54bbf4a0115dbf88e03"},"schema_version":"1.0"},"canonical_sha256":"e9ab8bb4bea68c4ba1b8b5c4a5c54cc405ce197d45e2831cd2b1583dd1888af5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:06.120289Z","signature_b64":"SYxz/2oMFZDeoL/pLQMrRIMFf5tqH2dGwVAq1peIePQPgORNzFOCh8/CJU80vKftvsSEkMxToMlZ0K/OsngMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ab8bb4bea68c4ba1b8b5c4a5c54cc405ce197d45e2831cd2b1583dd1888af5","last_reissued_at":"2026-07-05T01:00:06.119887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:06.119887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.01278","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":"2026-07-05T01:00:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RekgcJxak+o6xFxuuvi1NXbWeIir6BfapoFAWEmNa3Ba275N+ehFyVDfbvX5UYyNfI2j0W593UosB4lXdCN8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:17:01.799436Z"},"content_sha256":"81d53c3dfded3ca8e36e247d83e8c3ed8935e988a016d54969c68bcaf3169edc","schema_version":"1.0","event_id":"sha256:81d53c3dfded3ca8e36e247d83e8c3ed8935e988a016d54969c68bcaf3169edc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5GVYXNF6U2GEXINYWXCKLRKMYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Yang Zhang, Zhiqiang Zhan, Zifeng Hou","submitted_at":"2020-05-04T05:20:19Z","abstract_excerpt":"Recent neural models have shown significant progress in dialogue generation. Most generation models are based on language models. However, due to the Long Tail Phenomenon in linguistics, the trained models tend to generate words that appear frequently in training datasets, leading to a monotonous issue. To address this issue, we analyze a large corpus from Wikipedia and propose three frequency-based data normalization methods. We conduct extensive experiments based on transformers and three datasets respectively collected from social media, subtitles, and the industrial application. Experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01278","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.01278/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:00:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4OV21B9tp/aOGaVW1TgGzuOpDC28LNZpccQ07dfPpWIx+iq8Gbbj2h0JdacPhTLg3bFz2atIMxSjvT04adsmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:17:01.799838Z"},"content_sha256":"886404ef04be1a3132d5ee0de0b13b594dd2a39597958f4cd924585902008e87","schema_version":"1.0","event_id":"sha256:886404ef04be1a3132d5ee0de0b13b594dd2a39597958f4cd924585902008e87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5GVYXNF6U2GEXINYWXCKLRKMYQ/bundle.json","state_url":"https://pith.science/pith/5GVYXNF6U2GEXINYWXCKLRKMYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5GVYXNF6U2GEXINYWXCKLRKMYQ/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":"2026-08-24T02:17:01Z","links":{"resolver":"https://pith.science/pith/5GVYXNF6U2GEXINYWXCKLRKMYQ","bundle":"https://pith.science/pith/5GVYXNF6U2GEXINYWXCKLRKMYQ/bundle.json","state":"https://pith.science/pith/5GVYXNF6U2GEXINYWXCKLRKMYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5GVYXNF6U2GEXINYWXCKLRKMYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5GVYXNF6U2GEXINYWXCKLRKMYQ","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":"8103406fcbc8d217d14b532364706dcfc4c984891324e54bbf4a0115dbf88e03","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T05:20:19Z","title_canon_sha256":"d1f04785e5f374e74cd587dc6a136c0f88ed5e1f78ff7209915a721b7281c82d"},"schema_version":"1.0","source":{"id":"2005.01278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01278","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01278v1","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01278","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"pith_short_12","alias_value":"5GVYXNF6U2GE","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"pith_short_16","alias_value":"5GVYXNF6U2GEXINY","created_at":"2026-07-05T01:00:06Z"},{"alias_kind":"pith_short_8","alias_value":"5GVYXNF6","created_at":"2026-07-05T01:00:06Z"}],"graph_snapshots":[{"event_id":"sha256:886404ef04be1a3132d5ee0de0b13b594dd2a39597958f4cd924585902008e87","target":"graph","created_at":"2026-07-05T01:00:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.01278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent neural models have shown significant progress in dialogue generation. Most generation models are based on language models. However, due to the Long Tail Phenomenon in linguistics, the trained models tend to generate words that appear frequently in training datasets, leading to a monotonous issue. To address this issue, we analyze a large corpus from Wikipedia and propose three frequency-based data normalization methods. We conduct extensive experiments based on transformers and three datasets respectively collected from social media, subtitles, and the industrial application. Experiment","authors_text":"Yang Zhang, Zhiqiang Zhan, Zifeng Hou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T05:20:19Z","title":"A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01278","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":"sha256:81d53c3dfded3ca8e36e247d83e8c3ed8935e988a016d54969c68bcaf3169edc","target":"record","created_at":"2026-07-05T01:00:06Z","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":"8103406fcbc8d217d14b532364706dcfc4c984891324e54bbf4a0115dbf88e03","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T05:20:19Z","title_canon_sha256":"d1f04785e5f374e74cd587dc6a136c0f88ed5e1f78ff7209915a721b7281c82d"},"schema_version":"1.0","source":{"id":"2005.01278","kind":"arxiv","version":1}},"canonical_sha256":"e9ab8bb4bea68c4ba1b8b5c4a5c54cc405ce197d45e2831cd2b1583dd1888af5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9ab8bb4bea68c4ba1b8b5c4a5c54cc405ce197d45e2831cd2b1583dd1888af5","first_computed_at":"2026-07-05T01:00:06.119887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:06.119887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SYxz/2oMFZDeoL/pLQMrRIMFf5tqH2dGwVAq1peIePQPgORNzFOCh8/CJU80vKftvsSEkMxToMlZ0K/OsngMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:06.120289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.01278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81d53c3dfded3ca8e36e247d83e8c3ed8935e988a016d54969c68bcaf3169edc","sha256:886404ef04be1a3132d5ee0de0b13b594dd2a39597958f4cd924585902008e87"],"state_sha256":"1f078bd64c4d650464a2db6f0bc81e5cd9835865c97ec8c484a56bb050f3621a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fcsqQQdBFk2P5Pj3S85VsMeSjNpIvVTIVWyrGkIr+mFD3G+CYvEHzMhNazqDbzFhDHRADw/MAiMaeKT6CtMwDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T02:17:01.803759Z","bundle_sha256":"f15141d1ddb6bd5c0f49231bc06381c69d8bf6de2044ad9cd6c448846bf07cf3"}}