{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:E3BHYDTPBYZDTNPBZQMUHE27TS","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":"8ddd1fb8b23fb2b2d916fa971a946f15561b419c1c747158cf3957e6b3a15e97","cross_cats_sorted":["cs.CL","cs.CV","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-15T15:09:32Z","title_canon_sha256":"e605eb4afcd3d8e27a6737e5db2cb87e04ccdaa25a117283ce88392c5f2f761c"},"schema_version":"1.0","source":{"id":"2104.07511","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07511","created_at":"2026-07-05T03:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07511v3","created_at":"2026-07-05T03:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07511","created_at":"2026-07-05T03:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"E3BHYDTPBYZD","created_at":"2026-07-05T03:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"E3BHYDTPBYZDTNPB","created_at":"2026-07-05T03:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"E3BHYDTP","created_at":"2026-07-05T03:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:48704862706fd1303ac5684dad30a15a009ffce67d022c7a361002477052aa3e","target":"graph","created_at":"2026-07-05T03:03:19Z","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/2104.07511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Assessing an AI agent that can converse in human language and understand visual content is challenging. Generation metrics, such as BLEU scores favor correct syntax over semantics. Hence a discriminative approach is often used, where an agent ranks a set of candidate options. The mean reciprocal rank (MRR) metric evaluates the model performance by taking into account the rank of a single human-derived answer. This approach, however, raises a new challenge: the ambiguity and synonymy of answers, for instance, semantic equivalence (e.g., `yeah' and `yes'). To address this, the normalized discoun","authors_text":"Idan Schwartz","cross_cats":["cs.CL","cs.CV","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-15T15:09:32Z","title":"Ensemble of MRR and NDCG models for Visual Dialog"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07511","kind":"arxiv","version":3},"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:a7f8922a89d046573883d358bf3543569c5eab350280a6c17a7cc6adce0de0a2","target":"record","created_at":"2026-07-05T03:03:19Z","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":"8ddd1fb8b23fb2b2d916fa971a946f15561b419c1c747158cf3957e6b3a15e97","cross_cats_sorted":["cs.CL","cs.CV","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-04-15T15:09:32Z","title_canon_sha256":"e605eb4afcd3d8e27a6737e5db2cb87e04ccdaa25a117283ce88392c5f2f761c"},"schema_version":"1.0","source":{"id":"2104.07511","kind":"arxiv","version":3}},"canonical_sha256":"26c27c0e6f0e3239b5e1cc1943935f9cb202d2efc7387316cc2e3c65b8b30d54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26c27c0e6f0e3239b5e1cc1943935f9cb202d2efc7387316cc2e3c65b8b30d54","first_computed_at":"2026-07-05T03:03:19.528615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:19.528615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1MnKg2L/3FimQS4DQADD1xeEEETuf9onglIy8LCApgC8tiP0eMQ3LDr2SpQsQu51EY0YDFnWJtrG/rj2M07+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:19.529115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07511","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7f8922a89d046573883d358bf3543569c5eab350280a6c17a7cc6adce0de0a2","sha256:48704862706fd1303ac5684dad30a15a009ffce67d022c7a361002477052aa3e"],"state_sha256":"e76e8f7902b680c6a490cc1e5439e79d2519a4ac880d828628c339d1a9171dde"}