{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I7VOKK5PKSZS6E4XIWBAIPTNJN","short_pith_number":"pith:I7VOKK5P","schema_version":"1.0","canonical_sha256":"47eae52baf54b32f13974582043e6d4b63893f60fe3ac7669044222598c7a87c","source":{"kind":"arxiv","id":"1902.08832","version":1},"attestation_state":"computed","paper":{"title":"Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya B. Sai, Mitesh M. Khapra, Mithun Das Gupta, Mukundhan Srinivasan","submitted_at":"2019-02-23T19:21:24Z","abstract_excerpt":"Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. ADEM(Lowe et al. 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able to predict responses which correlate significantly with human judgements, both at utterance and system level. Their system was shown to have beaten word-overlap metrics such as BLEU with large margins. We start with the question of whether an adversary can game the ADEM model. We design a battery of targeted attacks at the neural network based ADEM "},"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":"1902.08832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T19:21:24Z","cross_cats_sorted":[],"title_canon_sha256":"1786244489adc242a923451f62709935950bae59be9d83f62e1e839ad2e4f49a","abstract_canon_sha256":"2644917bf349f6be176823fddbc159f76a9c62214afad062d5e04d41178ab0d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:49.759876Z","signature_b64":"g0Dhk80wuETuuXYDVcgJL/AFPQwj8kU4aB49bCbV/cqnJUx3yDMIcy+TntgnFzBOZUblBRzCRzmNmnBwFTwtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47eae52baf54b32f13974582043e6d4b63893f60fe3ac7669044222598c7a87c","last_reissued_at":"2026-05-17T23:52:49.759011Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:49.759011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya B. Sai, Mitesh M. Khapra, Mithun Das Gupta, Mukundhan Srinivasan","submitted_at":"2019-02-23T19:21:24Z","abstract_excerpt":"Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. ADEM(Lowe et al. 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able to predict responses which correlate significantly with human judgements, both at utterance and system level. Their system was shown to have beaten word-overlap metrics such as BLEU with large margins. We start with the question of whether an adversary can game the ADEM model. We design a battery of targeted attacks at the neural network based ADEM "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08832","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":""},"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":"1902.08832","created_at":"2026-05-17T23:52:49.759167+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.08832v1","created_at":"2026-05-17T23:52:49.759167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08832","created_at":"2026-05-17T23:52:49.759167+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7VOKK5PKSZS","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7VOKK5PKSZS6E4X","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7VOKK5P","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN","json":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN.json","graph_json":"https://pith.science/api/pith-number/I7VOKK5PKSZS6E4XIWBAIPTNJN/graph.json","events_json":"https://pith.science/api/pith-number/I7VOKK5PKSZS6E4XIWBAIPTNJN/events.json","paper":"https://pith.science/paper/I7VOKK5P"},"agent_actions":{"view_html":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN","download_json":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN.json","view_paper":"https://pith.science/paper/I7VOKK5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.08832&json=true","fetch_graph":"https://pith.science/api/pith-number/I7VOKK5PKSZS6E4XIWBAIPTNJN/graph.json","fetch_events":"https://pith.science/api/pith-number/I7VOKK5PKSZS6E4XIWBAIPTNJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/action/storage_attestation","attest_author":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/action/author_attestation","sign_citation":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/action/citation_signature","submit_replication":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/action/replication_record"}},"created_at":"2026-05-17T23:52:49.759167+00:00","updated_at":"2026-05-17T23:52:49.759167+00:00"}