{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HGGV3EW64AISIHAUYEQJA2HZ7J","short_pith_number":"pith:HGGV3EW6","canonical_record":{"source":{"id":"2004.14302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T16:21:50Z","cross_cats_sorted":[],"title_canon_sha256":"395ce2f138347dea137ea45a3f61cd8008ee14bea72943af9856caed69c442a9","abstract_canon_sha256":"3e854c73012ead275b4bba2c0e354ccb36b0297fc3bd9551cb06490746814ef9"},"schema_version":"1.0"},"canonical_sha256":"398d5d92dee011241c14c1209068f9fa601a2eaa7c5c63a084ab2d6607b364ce","source":{"kind":"arxiv","id":"2004.14302","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14302","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14302v1","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14302","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"HGGV3EW64AIS","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"HGGV3EW64AISIHAU","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"HGGV3EW6","created_at":"2026-07-05T00:59:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HGGV3EW64AISIHAUYEQJA2HZ7J","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T16:21:50Z","cross_cats_sorted":[],"title_canon_sha256":"395ce2f138347dea137ea45a3f61cd8008ee14bea72943af9856caed69c442a9","abstract_canon_sha256":"3e854c73012ead275b4bba2c0e354ccb36b0297fc3bd9551cb06490746814ef9"},"schema_version":"1.0"},"canonical_sha256":"398d5d92dee011241c14c1209068f9fa601a2eaa7c5c63a084ab2d6607b364ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:19.404009Z","signature_b64":"rMaTS79eC+oVBzD+P3p9vzaIaAp/srzhHAFpG2XYUynQExhM5FS3m21NydLuxDIciBGPy/NN9+47b+UtMbRJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"398d5d92dee011241c14c1209068f9fa601a2eaa7c5c63a084ab2d6607b364ce","last_reissued_at":"2026-07-05T00:59:19.403644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:19.403644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14302","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":"2026-07-05T00:59:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1sOQdvQ7anjUQh48BOn8g2ApudXmLXAT0ED2cHhFNQBDDsuyIhzQrCbyp3VhvVzFSB71lwO+eC9ZKIl4SElJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:02:54.160203Z"},"content_sha256":"8da8e4df44660091c820a77bd59b213edc394e3006a5dae146b658567b130cab","schema_version":"1.0","event_id":"sha256:8da8e4df44660091c820a77bd59b213edc394e3006a5dae146b658567b130cab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HGGV3EW64AISIHAUYEQJA2HZ7J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Dialogue Generation Systems via Response Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hiroki Ouchi, Jun Suzuki, Kentaro Inui, Reina Akama, Shiki Sato","submitted_at":"2020-04-29T16:21:50Z","abstract_excerpt":"Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation systems via response selection. To evaluate systems properly via response selection, we propose the method to construct response selection test sets with well-chosen false candidates. Specifically, we propose to construct test sets filtering out some types of false candidates: (i) those unrelated to the ground-truth response and (ii) those acceptable as appropriate responses. Through experiments, we demonstrate that evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14302","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/2004.14302/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":"2026-07-05T00:59:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5puFoD1ZeeFftY5LbsR875FB8HqcuS7XpCYU6lqahSUV256qj38E2lzEympgfquDZmnlOmxH7Gwn16mPuZpGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:02:54.160727Z"},"content_sha256":"c9d07567f76c0797b821c581c39d0c16c73c7491781008cc4026c1152a153baf","schema_version":"1.0","event_id":"sha256:c9d07567f76c0797b821c581c39d0c16c73c7491781008cc4026c1152a153baf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HGGV3EW64AISIHAUYEQJA2HZ7J/bundle.json","state_url":"https://pith.science/pith/HGGV3EW64AISIHAUYEQJA2HZ7J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HGGV3EW64AISIHAUYEQJA2HZ7J/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":"2026-08-17T03:02:54Z","links":{"resolver":"https://pith.science/pith/HGGV3EW64AISIHAUYEQJA2HZ7J","bundle":"https://pith.science/pith/HGGV3EW64AISIHAUYEQJA2HZ7J/bundle.json","state":"https://pith.science/pith/HGGV3EW64AISIHAUYEQJA2HZ7J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HGGV3EW64AISIHAUYEQJA2HZ7J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HGGV3EW64AISIHAUYEQJA2HZ7J","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":"3e854c73012ead275b4bba2c0e354ccb36b0297fc3bd9551cb06490746814ef9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T16:21:50Z","title_canon_sha256":"395ce2f138347dea137ea45a3f61cd8008ee14bea72943af9856caed69c442a9"},"schema_version":"1.0","source":{"id":"2004.14302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14302","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14302v1","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14302","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"HGGV3EW64AIS","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"HGGV3EW64AISIHAU","created_at":"2026-07-05T00:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"HGGV3EW6","created_at":"2026-07-05T00:59:19Z"}],"graph_snapshots":[{"event_id":"sha256:c9d07567f76c0797b821c581c39d0c16c73c7491781008cc4026c1152a153baf","target":"graph","created_at":"2026-07-05T00:59:19Z","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/2004.14302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation systems via response selection. To evaluate systems properly via response selection, we propose the method to construct response selection test sets with well-chosen false candidates. Specifically, we propose to construct test sets filtering out some types of false candidates: (i) those unrelated to the ground-truth response and (ii) those acceptable as appropriate responses. Through experiments, we demonstrate that evalua","authors_text":"Hiroki Ouchi, Jun Suzuki, Kentaro Inui, Reina Akama, Shiki Sato","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T16:21:50Z","title":"Evaluating Dialogue Generation Systems via Response Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14302","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":"sha256:8da8e4df44660091c820a77bd59b213edc394e3006a5dae146b658567b130cab","target":"record","created_at":"2026-07-05T00:59:19Z","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":"3e854c73012ead275b4bba2c0e354ccb36b0297fc3bd9551cb06490746814ef9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T16:21:50Z","title_canon_sha256":"395ce2f138347dea137ea45a3f61cd8008ee14bea72943af9856caed69c442a9"},"schema_version":"1.0","source":{"id":"2004.14302","kind":"arxiv","version":1}},"canonical_sha256":"398d5d92dee011241c14c1209068f9fa601a2eaa7c5c63a084ab2d6607b364ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"398d5d92dee011241c14c1209068f9fa601a2eaa7c5c63a084ab2d6607b364ce","first_computed_at":"2026-07-05T00:59:19.403644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:19.403644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rMaTS79eC+oVBzD+P3p9vzaIaAp/srzhHAFpG2XYUynQExhM5FS3m21NydLuxDIciBGPy/NN9+47b+UtMbRJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:19.404009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8da8e4df44660091c820a77bd59b213edc394e3006a5dae146b658567b130cab","sha256:c9d07567f76c0797b821c581c39d0c16c73c7491781008cc4026c1152a153baf"],"state_sha256":"7dcfd6d677f45e24d7e582878c95ce15416ca69de7ef0f78b2b70621dfc6b775"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJ6jotz4gZw4SVbDMubpiBtAci7bs1J7PER9cxLdNoS93jiUi3sKtf73A8iEVnF+SgyJ7t1d2SAE1IA7uOW3DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T03:02:54.259655Z","bundle_sha256":"1c3009edae51daeaed7f50402b2d509c3caf98ac26c91e2474345e74e74aacf4"}}