{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Q5SJSCVLTFJW7MBGSDS2RGPCYL","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":"68f3bed05c1632befa259275bec14be1ff1586a7f1cf8856346ee50475571db9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-23T18:06:52Z","title_canon_sha256":"a6b8557d535ba77ff24658d6c029f312e65d65b34592580efaf80368a25fc7c1"},"schema_version":"1.0","source":{"id":"2009.11321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.11321","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"arxiv_version","alias_value":"2009.11321v1","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.11321","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"pith_short_12","alias_value":"Q5SJSCVLTFJW","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"pith_short_16","alias_value":"Q5SJSCVLTFJW7MBG","created_at":"2026-07-05T01:37:44Z"},{"alias_kind":"pith_short_8","alias_value":"Q5SJSCVL","created_at":"2026-07-05T01:37:44Z"}],"graph_snapshots":[{"event_id":"sha256:ba68ec3fabac6c02ca7b2c3b1e57144ae68add38ca23e617883b8118b7935d73","target":"graph","created_at":"2026-07-05T01:37:44Z","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/2009.11321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is an increasing focus on model-based dialog evaluation metrics such as ADEM, RUBER, and the more recent BERT-based metrics. These models aim to assign a high score to all relevant responses and a low score to all irrelevant responses. Ideally, such models should be trained using multiple relevant and irrelevant responses for any given context. However, no such data is publicly available, and hence existing models are usually trained using a single relevant response and multiple randomly selected responses from other contexts (random negatives). To allow for better training and robust ev","authors_text":"Akash Kumar Mohankumar, Ananya B. Sai, Mitesh M. Khapra, Siddhartha Arora","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-23T18:06:52Z","title":"Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.11321","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:ba2054dbb34e497c55bfdf9d9ed3f66cd615e39a8f105dbacd59cb322b42dca8","target":"record","created_at":"2026-07-05T01:37:44Z","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":"68f3bed05c1632befa259275bec14be1ff1586a7f1cf8856346ee50475571db9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-23T18:06:52Z","title_canon_sha256":"a6b8557d535ba77ff24658d6c029f312e65d65b34592580efaf80368a25fc7c1"},"schema_version":"1.0","source":{"id":"2009.11321","kind":"arxiv","version":1}},"canonical_sha256":"8764990aab99536fb02690e5a899e2c2f65e03797b29c928959703f5d540e13b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8764990aab99536fb02690e5a899e2c2f65e03797b29c928959703f5d540e13b","first_computed_at":"2026-07-05T01:37:44.581739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:44.581739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IFu/tkDpvBlqQlAPyfrVoowDJXN6+SYR8kI+XphbGGKnQ0ablmPm2GdgzTAZmlp7h7h8HmopPJtZi6hPHbAQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:44.582097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.11321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba2054dbb34e497c55bfdf9d9ed3f66cd615e39a8f105dbacd59cb322b42dca8","sha256:ba68ec3fabac6c02ca7b2c3b1e57144ae68add38ca23e617883b8118b7935d73"],"state_sha256":"04e435c51672f8592e5e1db43e07840b578edf4776c4885e4d7247f447fba47b"}