{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PR3YKX24L52EHBADDNVSUU7OVR","short_pith_number":"pith:PR3YKX24","canonical_record":{"source":{"id":"2303.09719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T01:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"6bf52923d63563728c832fec1fbc58fc56be4ecc0a105695b7a6064c014bd7ac","abstract_canon_sha256":"efefa3ddb50a67f75595520cf22a70d6a8a47224a4bde36d52fc2fdf29f3da53"},"schema_version":"1.0"},"canonical_sha256":"7c77855f5c5f744384031b6b2a53eeac46090c27f9857ed67dbe68e27785194b","source":{"kind":"arxiv","id":"2303.09719","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09719","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09719v1","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09719","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"pith_short_12","alias_value":"PR3YKX24L52E","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"pith_short_16","alias_value":"PR3YKX24L52EHBAD","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"pith_short_8","alias_value":"PR3YKX24","created_at":"2026-07-05T05:52:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PR3YKX24L52EHBADDNVSUU7OVR","target":"record","payload":{"canonical_record":{"source":{"id":"2303.09719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T01:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"6bf52923d63563728c832fec1fbc58fc56be4ecc0a105695b7a6064c014bd7ac","abstract_canon_sha256":"efefa3ddb50a67f75595520cf22a70d6a8a47224a4bde36d52fc2fdf29f3da53"},"schema_version":"1.0"},"canonical_sha256":"7c77855f5c5f744384031b6b2a53eeac46090c27f9857ed67dbe68e27785194b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:10.864279Z","signature_b64":"zDL50vqR0jsRb1wXsv7y1BLy/5RFFpL4XCXJOFnd29pdJYOoXHZl6eP5TYRXSWiRVEXiRQ1l3UwbAsWhoO4OCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c77855f5c5f744384031b6b2a53eeac46090c27f9857ed67dbe68e27785194b","last_reissued_at":"2026-07-05T05:52:10.863806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:10.863806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.09719","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":"2026-07-05T05:52:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OxMR3WPqcP64XRLxOR7LWSrFjCtZNNB1bSzaxZH7yD0q+QFCyBka6HaW/3/ecAA2uLtpKXJRnSdjHwBMzopPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:32:40.119777Z"},"content_sha256":"31cd6525c6e51b57be06124811a1276cca9be40a1a095ba040943b62d0f4cb99","schema_version":"1.0","event_id":"sha256:31cd6525c6e51b57be06124811a1276cca9be40a1a095ba040943b62d0f4cb99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PR3YKX24L52EHBADDNVSUU7OVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning towards Selective Data Augmentation for Dialogue Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Wei, Jianwei Cui, Jiayi Zhang, Mingzhe Li, Rui Yan, Xiangliang Zhang, Xiaoqiang Xia, Xin Gao, Xiuying Chen","submitted_at":"2023-03-17T01:26:39Z","abstract_excerpt":"As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the dialog generation task mostly augment all cases in the training dataset without considering the intrinsic attributes between different cases. We argue that not all cases are beneficial for augmentation task, and the cases suitable for augmentation should obey the following two attributes: (1) low-quality (the dialog model cannot generate a high-quality response f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09719","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/2303.09719/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":"2026-07-05T05:52:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gbmi30qnLLe/ykSzP6GFOg8JPOjW06hoKrUgDex6QO9Haz6zevCmtIX5MNmOXGTkI8DUYyk8hKZnp6HY+JNGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:32:40.120259Z"},"content_sha256":"12a75f08e0c53a0f6d1d47766e7fcb3ea472e26e8ae833f7ea07b4959483352b","schema_version":"1.0","event_id":"sha256:12a75f08e0c53a0f6d1d47766e7fcb3ea472e26e8ae833f7ea07b4959483352b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PR3YKX24L52EHBADDNVSUU7OVR/bundle.json","state_url":"https://pith.science/pith/PR3YKX24L52EHBADDNVSUU7OVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PR3YKX24L52EHBADDNVSUU7OVR/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":"2026-08-05T00:32:40Z","links":{"resolver":"https://pith.science/pith/PR3YKX24L52EHBADDNVSUU7OVR","bundle":"https://pith.science/pith/PR3YKX24L52EHBADDNVSUU7OVR/bundle.json","state":"https://pith.science/pith/PR3YKX24L52EHBADDNVSUU7OVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PR3YKX24L52EHBADDNVSUU7OVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PR3YKX24L52EHBADDNVSUU7OVR","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":"efefa3ddb50a67f75595520cf22a70d6a8a47224a4bde36d52fc2fdf29f3da53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T01:26:39Z","title_canon_sha256":"6bf52923d63563728c832fec1fbc58fc56be4ecc0a105695b7a6064c014bd7ac"},"schema_version":"1.0","source":{"id":"2303.09719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09719","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09719v1","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09719","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"pith_short_12","alias_value":"PR3YKX24L52E","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"pith_short_16","alias_value":"PR3YKX24L52EHBAD","created_at":"2026-07-05T05:52:10Z"},{"alias_kind":"pith_short_8","alias_value":"PR3YKX24","created_at":"2026-07-05T05:52:10Z"}],"graph_snapshots":[{"event_id":"sha256:12a75f08e0c53a0f6d1d47766e7fcb3ea472e26e8ae833f7ea07b4959483352b","target":"graph","created_at":"2026-07-05T05:52:10Z","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/2303.09719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the dialog generation task mostly augment all cases in the training dataset without considering the intrinsic attributes between different cases. We argue that not all cases are beneficial for augmentation task, and the cases suitable for augmentation should obey the following two attributes: (1) low-quality (the dialog model cannot generate a high-quality response f","authors_text":"Chen Wei, Jianwei Cui, Jiayi Zhang, Mingzhe Li, Rui Yan, Xiangliang Zhang, Xiaoqiang Xia, Xin Gao, Xiuying Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T01:26:39Z","title":"Learning towards Selective Data Augmentation for Dialogue Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09719","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":"sha256:31cd6525c6e51b57be06124811a1276cca9be40a1a095ba040943b62d0f4cb99","target":"record","created_at":"2026-07-05T05:52:10Z","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":"efefa3ddb50a67f75595520cf22a70d6a8a47224a4bde36d52fc2fdf29f3da53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T01:26:39Z","title_canon_sha256":"6bf52923d63563728c832fec1fbc58fc56be4ecc0a105695b7a6064c014bd7ac"},"schema_version":"1.0","source":{"id":"2303.09719","kind":"arxiv","version":1}},"canonical_sha256":"7c77855f5c5f744384031b6b2a53eeac46090c27f9857ed67dbe68e27785194b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c77855f5c5f744384031b6b2a53eeac46090c27f9857ed67dbe68e27785194b","first_computed_at":"2026-07-05T05:52:10.863806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:10.863806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zDL50vqR0jsRb1wXsv7y1BLy/5RFFpL4XCXJOFnd29pdJYOoXHZl6eP5TYRXSWiRVEXiRQ1l3UwbAsWhoO4OCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:10.864279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31cd6525c6e51b57be06124811a1276cca9be40a1a095ba040943b62d0f4cb99","sha256:12a75f08e0c53a0f6d1d47766e7fcb3ea472e26e8ae833f7ea07b4959483352b"],"state_sha256":"8be1939218b602056247ed9235e7235201cfa987d91e4d2ef91b3628fcf18c69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7U2a4AHD+MgVFzdImMRX34A/sP+MKMpRwNjUdMM9TcPOXZMFxa4bGmk7Hob/R8M5m8ZNt2pnBkjnr4qeeiM2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:32:40.123327Z","bundle_sha256":"7bb8359bc84efe1e925f028384e25a33f0d7cfdd4c4346937e82fbc06f65263d"}}