{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:I7VOKK5PKSZS6E4XIWBAIPTNJN","short_pith_number":"pith:I7VOKK5P","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"},"canonical_sha256":"47eae52baf54b32f13974582043e6d4b63893f60fe3ac7669044222598c7a87c","source":{"kind":"arxiv","id":"1902.08832","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08832","created_at":"2026-05-17T23:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08832v1","created_at":"2026-05-17T23:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08832","created_at":"2026-05-17T23:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"I7VOKK5PKSZS","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"I7VOKK5PKSZS6E4X","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"I7VOKK5P","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:I7VOKK5PKSZS6E4XIWBAIPTNJN","target":"record","payload":{"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"},"canonical_sha256":"47eae52baf54b32f13974582043e6d4b63893f60fe3ac7669044222598c7a87c","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"},"source_kind":"arxiv","source_id":"1902.08832","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":"2026-05-17T23:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2SUE7/5PKSgNrXE3gsIbogU3euWXrCr9nJekMdH6/3gnVfMTuXU0YM9S1eqaWIcA7ONOLMiWeih1txE2K6kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:04:51.780778Z"},"content_sha256":"41e3591a00360fed6af28b674e76aa8de5079e17650fa8db77f633181aadbf07","schema_version":"1.0","event_id":"sha256:41e3591a00360fed6af28b674e76aa8de5079e17650fa8db77f633181aadbf07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:I7VOKK5PKSZS6E4XIWBAIPTNJN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgneQH6aw45DVVEwZz+s0s3XexF2Fdlx2wxI7m+lQRyyjCRLmnPJdqfn/1gavPp3rwdV7hHnEpztWbGEtQDrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:04:51.781459Z"},"content_sha256":"ab31122c2f90b47b2def233625251317b88b77925c7553f121b3b04c026d2f23","schema_version":"1.0","event_id":"sha256:ab31122c2f90b47b2def233625251317b88b77925c7553f121b3b04c026d2f23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/bundle.json","state_url":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/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":"2026-05-30T09:04:51Z","links":{"resolver":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN","bundle":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/bundle.json","state":"https://pith.science/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I7VOKK5PKSZS6E4XIWBAIPTNJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:I7VOKK5PKSZS6E4XIWBAIPTNJN","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":"2644917bf349f6be176823fddbc159f76a9c62214afad062d5e04d41178ab0d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T19:21:24Z","title_canon_sha256":"1786244489adc242a923451f62709935950bae59be9d83f62e1e839ad2e4f49a"},"schema_version":"1.0","source":{"id":"1902.08832","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08832","created_at":"2026-05-17T23:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08832v1","created_at":"2026-05-17T23:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08832","created_at":"2026-05-17T23:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"I7VOKK5PKSZS","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"I7VOKK5PKSZS6E4X","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"I7VOKK5P","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:ab31122c2f90b47b2def233625251317b88b77925c7553f121b3b04c026d2f23","target":"graph","created_at":"2026-05-17T23:52:49Z","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"},"paper":{"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 ","authors_text":"Ananya B. Sai, Mitesh M. Khapra, Mithun Das Gupta, Mukundhan Srinivasan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T19:21:24Z","title":"Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08832","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":"sha256:41e3591a00360fed6af28b674e76aa8de5079e17650fa8db77f633181aadbf07","target":"record","created_at":"2026-05-17T23:52:49Z","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":"2644917bf349f6be176823fddbc159f76a9c62214afad062d5e04d41178ab0d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T19:21:24Z","title_canon_sha256":"1786244489adc242a923451f62709935950bae59be9d83f62e1e839ad2e4f49a"},"schema_version":"1.0","source":{"id":"1902.08832","kind":"arxiv","version":1}},"canonical_sha256":"47eae52baf54b32f13974582043e6d4b63893f60fe3ac7669044222598c7a87c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47eae52baf54b32f13974582043e6d4b63893f60fe3ac7669044222598c7a87c","first_computed_at":"2026-05-17T23:52:49.759011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:49.759011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g0Dhk80wuETuuXYDVcgJL/AFPQwj8kU4aB49bCbV/cqnJUx3yDMIcy+TntgnFzBOZUblBRzCRzmNmnBwFTwtAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:49.759876Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.08832","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e3591a00360fed6af28b674e76aa8de5079e17650fa8db77f633181aadbf07","sha256:ab31122c2f90b47b2def233625251317b88b77925c7553f121b3b04c026d2f23"],"state_sha256":"9c098be7ab519c664e3dc949e555808dfe3a4fc33c98d1e0d3131cbeba1a23e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmafxmcbFOhZhyCOD2QxyrNrmcchXd7ZyENa2MD3gITjHO/k2zq0ue9SiS/d9Q5+Kry6LxeDGPJzVpCagQBMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:04:51.785900Z","bundle_sha256":"17065e6ac2957458dc9f8c20b086c2159154d2aaef9381429739b9affe08ab4b"}}