{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RDYNVENAU3PTVLBJ4MPNZGCWXE","short_pith_number":"pith:RDYNVENA","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"},"canonical_sha256":"88f0da91a0a6df3aac29e31edc9856b935f95454ea2b10d127b78d8345ccde0d","source":{"kind":"arxiv","id":"1905.05471","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05471","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05471v3","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05471","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"RDYNVENAU3PT","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"RDYNVENAU3PTVLBJ","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"RDYNVENA","created_at":"2026-07-04T23:51:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RDYNVENAU3PTVLBJ4MPNZGCWXE","target":"record","payload":{"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"},"canonical_sha256":"88f0da91a0a6df3aac29e31edc9856b935f95454ea2b10d127b78d8345ccde0d","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"},"source_kind":"arxiv","source_id":"1905.05471","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":"2026-07-04T23:51:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yy8F7EaVadSMuZHkMWibykyKmEEUv2Y3WoXJq43ewxR2wTyUyKnAx9eAnUosALxZhuKG/u7n43va60A1oCSVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:00:53.129474Z"},"content_sha256":"b0647be9a1cf1f90f895a224d210f2c1ec9fe206b56e7d9ec7531dda5401d14f","schema_version":"1.0","event_id":"sha256:b0647be9a1cf1f90f895a224d210f2c1ec9fe206b56e7d9ec7531dda5401d14f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RDYNVENAU3PTVLBJ4MPNZGCWXE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:51:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fVghfKpqnj6i6oCKAQ6FFR8qITRUMAmNszwt4qX47qTqrCMP6pa5sFRaSc0ysxwCohmH3e7Z+YXYm+0lJ8rNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:00:53.130002Z"},"content_sha256":"09872a3e27f826abad02d6411534530c1b7e8af3d848faca66b92bbb141e8d28","schema_version":"1.0","event_id":"sha256:09872a3e27f826abad02d6411534530c1b7e8af3d848faca66b92bbb141e8d28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/bundle.json","state_url":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/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":"2026-08-09T15:00:53Z","links":{"resolver":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE","bundle":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/bundle.json","state":"https://pith.science/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDYNVENAU3PTVLBJ4MPNZGCWXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RDYNVENAU3PTVLBJ4MPNZGCWXE","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":"61767974d9c8202652b10ef9b02bff13970de076e9d520de2b929e871e66cb3c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T09:07:30Z","title_canon_sha256":"ba5971d02303cd5185b83db45cb4cc2a5074aa16224bdcb634b3f1c2aad84d79"},"schema_version":"1.0","source":{"id":"1905.05471","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05471","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05471v3","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05471","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"RDYNVENAU3PT","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"RDYNVENAU3PTVLBJ","created_at":"2026-07-04T23:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"RDYNVENA","created_at":"2026-07-04T23:51:15Z"}],"graph_snapshots":[{"event_id":"sha256:09872a3e27f826abad02d6411534530c1b7e8af3d848faca66b92bbb141e8d28","target":"graph","created_at":"2026-07-04T23:51:15Z","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/1905.05471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gabor Recski, Patrik Purgai, Richard Csaky","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T09:07:30Z","title":"Improving Neural Conversational Models with Entropy-Based Data Filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05471","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:b0647be9a1cf1f90f895a224d210f2c1ec9fe206b56e7d9ec7531dda5401d14f","target":"record","created_at":"2026-07-04T23:51:15Z","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":"61767974d9c8202652b10ef9b02bff13970de076e9d520de2b929e871e66cb3c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T09:07:30Z","title_canon_sha256":"ba5971d02303cd5185b83db45cb4cc2a5074aa16224bdcb634b3f1c2aad84d79"},"schema_version":"1.0","source":{"id":"1905.05471","kind":"arxiv","version":3}},"canonical_sha256":"88f0da91a0a6df3aac29e31edc9856b935f95454ea2b10d127b78d8345ccde0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88f0da91a0a6df3aac29e31edc9856b935f95454ea2b10d127b78d8345ccde0d","first_computed_at":"2026-07-04T23:51:15.454633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:15.454633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aYWAJt66K0ZtsrT6ZeTqkAj53gKQNDUoOGNS0EAqE/5coAFJHWwBMhrZrEtfGXEwK/ofL/gQJ8c5xud9wJGaBQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:15.455084Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05471","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0647be9a1cf1f90f895a224d210f2c1ec9fe206b56e7d9ec7531dda5401d14f","sha256:09872a3e27f826abad02d6411534530c1b7e8af3d848faca66b92bbb141e8d28"],"state_sha256":"e16239c728df41c8f4d8fed3eb3d319504843b8b194a26533c8e0863ee7974b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bjpD934gl0DAeN94CHITdO3bqJHHZy6wDhNrCq46ybROHrbs/NAAz3leiDKBzPgUuFWLW+/xDPlaLLORfCyZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:00:53.133507Z","bundle_sha256":"06ec4872970f7a535b63c596fc8aa1f02671a6f9231557609c6a03fb1ec9e0d5"}}