{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VPPWWIXMPWKGWO5AFFRCOG23SD","short_pith_number":"pith:VPPWWIXM","canonical_record":{"source":{"id":"2201.06219","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-17T05:12:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50da42e923deeaf6cb1e2a29ac85baca17216b200d66f3b51ada77a1ef4137ec","abstract_canon_sha256":"7eff49ac9570b9600ba3f83919cf4e9d90a0605ca5cdcb600c2c0c5f6c271654"},"schema_version":"1.0"},"canonical_sha256":"abdf6b22ec7d946b3ba02962271b5b90d7663178f0d296768ea8e098a73521e3","source":{"kind":"arxiv","id":"2201.06219","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06219","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06219v2","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06219","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"VPPWWIXMPWKG","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"VPPWWIXMPWKGWO5A","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"VPPWWIXM","created_at":"2026-07-05T04:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VPPWWIXMPWKGWO5AFFRCOG23SD","target":"record","payload":{"canonical_record":{"source":{"id":"2201.06219","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-17T05:12:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50da42e923deeaf6cb1e2a29ac85baca17216b200d66f3b51ada77a1ef4137ec","abstract_canon_sha256":"7eff49ac9570b9600ba3f83919cf4e9d90a0605ca5cdcb600c2c0c5f6c271654"},"schema_version":"1.0"},"canonical_sha256":"abdf6b22ec7d946b3ba02962271b5b90d7663178f0d296768ea8e098a73521e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:08.956655Z","signature_b64":"HGbEyFuIpDZvZmrlB8X4Ze2Q5EFaDw25xYOkDIKEyn/RdnnN4SRav/XhfGDt3AtIsyyx9P2+dxt8Le1E2E3dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abdf6b22ec7d946b3ba02962271b5b90d7663178f0d296768ea8e098a73521e3","last_reissued_at":"2026-07-05T04:21:08.956169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:08.956169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.06219","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kYjYcP5qHRU2kENmRpXlyTLMDtgnhOCqUIVXGEANAm2D/m17NjqCxMv3COJqEoQeCvWTDhRvwiEumOhklwFeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:07:08.149402Z"},"content_sha256":"90c99d01ed3969d59b5267c8a4a438187a2b812ed6349c9bea648f81aa36f32e","schema_version":"1.0","event_id":"sha256:90c99d01ed3969d59b5267c8a4a438187a2b812ed6349c9bea648f81aa36f32e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VPPWWIXMPWKGWO5AFFRCOG23SD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guoqing Luo, Lili Mou, Yuqiao Wen","submitted_at":"2022-01-17T05:12:13Z","abstract_excerpt":"Open-domain dialogue systems aim to converse with humans through text, and dialogue research has heavily relied on benchmark datasets. In this work, we observe the overlapping problem in DailyDialog and OpenSubtitles, two popular open-domain dialogue benchmark datasets. Our systematic analysis then shows that such overlapping can be exploited to obtain fake state-of-the-art performance. Finally, we address this issue by cleaning these datasets and setting up a proper data processing procedure for future research."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06219","kind":"arxiv","version":2},"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/2201.06219/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":"2026-07-05T04:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIODexdIOly0D9NokaypfTueItTV8Nnfkg/9ZtTC4HcbpsWFTX5DXFmrZ2M1OwNCzA33swdwIW2XfEJfcBIfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:07:08.150165Z"},"content_sha256":"c1810c6c203374cdb2b528707ef362c22971835c7163b975c41b4f74bd47e11c","schema_version":"1.0","event_id":"sha256:c1810c6c203374cdb2b528707ef362c22971835c7163b975c41b4f74bd47e11c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPPWWIXMPWKGWO5AFFRCOG23SD/bundle.json","state_url":"https://pith.science/pith/VPPWWIXMPWKGWO5AFFRCOG23SD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPPWWIXMPWKGWO5AFFRCOG23SD/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":"2026-08-07T19:07:08Z","links":{"resolver":"https://pith.science/pith/VPPWWIXMPWKGWO5AFFRCOG23SD","bundle":"https://pith.science/pith/VPPWWIXMPWKGWO5AFFRCOG23SD/bundle.json","state":"https://pith.science/pith/VPPWWIXMPWKGWO5AFFRCOG23SD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPPWWIXMPWKGWO5AFFRCOG23SD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VPPWWIXMPWKGWO5AFFRCOG23SD","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":"7eff49ac9570b9600ba3f83919cf4e9d90a0605ca5cdcb600c2c0c5f6c271654","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-17T05:12:13Z","title_canon_sha256":"50da42e923deeaf6cb1e2a29ac85baca17216b200d66f3b51ada77a1ef4137ec"},"schema_version":"1.0","source":{"id":"2201.06219","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06219","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06219v2","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06219","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"VPPWWIXMPWKG","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"VPPWWIXMPWKGWO5A","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"VPPWWIXM","created_at":"2026-07-05T04:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:c1810c6c203374cdb2b528707ef362c22971835c7163b975c41b4f74bd47e11c","target":"graph","created_at":"2026-07-05T04:21:08Z","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/2201.06219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-domain dialogue systems aim to converse with humans through text, and dialogue research has heavily relied on benchmark datasets. In this work, we observe the overlapping problem in DailyDialog and OpenSubtitles, two popular open-domain dialogue benchmark datasets. Our systematic analysis then shows that such overlapping can be exploited to obtain fake state-of-the-art performance. Finally, we address this issue by cleaning these datasets and setting up a proper data processing procedure for future research.","authors_text":"Guoqing Luo, Lili Mou, Yuqiao Wen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-17T05:12:13Z","title":"An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06219","kind":"arxiv","version":2},"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":"sha256:90c99d01ed3969d59b5267c8a4a438187a2b812ed6349c9bea648f81aa36f32e","target":"record","created_at":"2026-07-05T04:21:08Z","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":"7eff49ac9570b9600ba3f83919cf4e9d90a0605ca5cdcb600c2c0c5f6c271654","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-17T05:12:13Z","title_canon_sha256":"50da42e923deeaf6cb1e2a29ac85baca17216b200d66f3b51ada77a1ef4137ec"},"schema_version":"1.0","source":{"id":"2201.06219","kind":"arxiv","version":2}},"canonical_sha256":"abdf6b22ec7d946b3ba02962271b5b90d7663178f0d296768ea8e098a73521e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abdf6b22ec7d946b3ba02962271b5b90d7663178f0d296768ea8e098a73521e3","first_computed_at":"2026-07-05T04:21:08.956169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:21:08.956169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HGbEyFuIpDZvZmrlB8X4Ze2Q5EFaDw25xYOkDIKEyn/RdnnN4SRav/XhfGDt3AtIsyyx9P2+dxt8Le1E2E3dBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:21:08.956655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.06219","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90c99d01ed3969d59b5267c8a4a438187a2b812ed6349c9bea648f81aa36f32e","sha256:c1810c6c203374cdb2b528707ef362c22971835c7163b975c41b4f74bd47e11c"],"state_sha256":"569a3444175f78bbb8c28cabc7865a5aeea3b56a816ea5d93b53f0cc14a3c617"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5HrvOfvdBSNxk9lb82V6g+0gcyJgBNig5DjfCG6rmsBLMwzLPU0FbEV3mo8YmKSWq7BVGUJrr12eQgSrUZNXBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:07:08.159392Z","bundle_sha256":"936b74868755297037cab834f9646b3060601157e5ffc10bd2a95c6627307b6f"}}