{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RDYNVENAU3PTVLBJ4MPNZGCWXE","short_pith_number":"pith:RDYNVENA","schema_version":"1.0","canonical_sha256":"88f0da91a0a6df3aac29e31edc9856b935f95454ea2b10d127b78d8345ccde0d","source":{"kind":"arxiv","id":"1905.05471","version":3},"attestation_state":"computed","paper":{"title":"Improving Neural Conversational Models with Entropy-Based Data Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabor Recski, Patrik Purgai, Richard Csaky","submitted_at":"2019-05-14T09:07:30Z","abstract_excerpt":"Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. Priors such as persona, emotion, or topic provide additional information to dialog models to aid response generation, but annotating a dataset with priors is expensive and such annotations are rarely available. While previous methods for improving the quality of open-domain response generation focused on either the underlying model or the training objective, we present a method of filtering dialog datasets by removing generic utterances from training data using a simple ent"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.05471","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T09:07:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba5971d02303cd5185b83db45cb4cc2a5074aa16224bdcb634b3f1c2aad84d79","abstract_canon_sha256":"61767974d9c8202652b10ef9b02bff13970de076e9d520de2b929e871e66cb3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:15.455084Z","signature_b64":"aYWAJt66K0ZtsrT6ZeTqkAj53gKQNDUoOGNS0EAqE/5coAFJHWwBMhrZrEtfGXEwK/ofL/gQJ8c5xud9wJGaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88f0da91a0a6df3aac29e31edc9856b935f95454ea2b10d127b78d8345ccde0d","last_reissued_at":"2026-07-04T23:51:15.454633Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:15.454633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Neural Conversational Models with Entropy-Based Data Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabor Recski, Patrik Purgai, Richard Csaky","submitted_at":"2019-05-14T09:07:30Z","abstract_excerpt":"Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. Priors such as persona, emotion, or topic provide additional information to dialog models to aid response generation, but annotating a dataset with priors is expensive and such annotations are rarely available. While previous methods for improving the quality of open-domain response generation focused on either the underlying model or the training objective, we present a method of filtering dialog datasets by removing generic utterances from training data using a simple ent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05471","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.05471/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.05471","created_at":"2026-07-04T23:51:15.454688+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05471v3","created_at":"2026-07-04T23:51:15.454688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05471","created_at":"2026-07-04T23:51:15.454688+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDYNVENAU3PT","created_at":"2026-07-04T23:51:15.454688+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDYNVENAU3PTVLBJ","created_at":"2026-07-04T23:51:15.454688+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDYNVENA","created_at":"2026-07-04T23:51:15.454688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11875","citing_title":"I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10915","citing_title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE","json":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE.json","graph_json":"https://pith.science/api/pith-number/RDYNVENAU3PTVLBJ4MPNZGCWXE/graph.json","events_json":"https://pith.science/api/pith-number/RDYNVENAU3PTVLBJ4MPNZGCWXE/events.json","paper":"https://pith.science/paper/RDYNVENA"},"agent_actions":{"view_html":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE","download_json":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE.json","view_paper":"https://pith.science/paper/RDYNVENA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05471&json=true","fetch_graph":"https://pith.science/api/pith-number/RDYNVENAU3PTVLBJ4MPNZGCWXE/graph.json","fetch_events":"https://pith.science/api/pith-number/RDYNVENAU3PTVLBJ4MPNZGCWXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/action/storage_attestation","attest_author":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/action/author_attestation","sign_citation":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/action/citation_signature","submit_replication":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/action/replication_record"}},"created_at":"2026-07-04T23:51:15.454688+00:00","updated_at":"2026-07-04T23:51:15.454688+00:00"}