{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UTJQLXLH3RFKVA3AGQWEKD4LGG","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":"de71e4794cd8390bc3c552c9a50f5ed9042b49cd931a7efe48cb1e8fbbbc031e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T20:45:14Z","title_canon_sha256":"6d4ef244486f1d0d55c841bb29e6e395f97b2fd53df1f3b4f36d9e28f61371d4"},"schema_version":"1.0","source":{"id":"2010.03644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03644","created_at":"2026-07-05T01:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03644v1","created_at":"2026-07-05T01:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03644","created_at":"2026-07-05T01:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"UTJQLXLH3RFK","created_at":"2026-07-05T01:41:21Z"},{"alias_kind":"pith_short_16","alias_value":"UTJQLXLH3RFKVA3A","created_at":"2026-07-05T01:41:21Z"},{"alias_kind":"pith_short_8","alias_value":"UTJQLXLH","created_at":"2026-07-05T01:41:21Z"}],"graph_snapshots":[{"event_id":"sha256:0057fee222dc5c26eafbf1ff556fe7c36c5903be5db9073b25e126e0ce0c1b52","target":"graph","created_at":"2026-07-05T01:41:21Z","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/2010.03644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A major challenge in visually grounded language generation is to build robust benchmark datasets and models that can generalize well in real-world settings. To do this, it is critical to ensure that our evaluation protocols are correct, and benchmarks are reliable. In this work, we set forth to design a set of experiments to understand an important but often ignored problem in visually grounded language generation: given that humans have different utilities and visual attention, how will the sample variance in multi-reference datasets affect the models' performance? Empirically, we study sever","authors_text":"Kazoo Sone, Pradyumna Narayana, Sugato Basu, Wanrong Zhu, William Yang Wang, Xin Eric Wang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T20:45:14Z","title":"Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03644","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":"sha256:1fa0282eb82453bac56516f9f77a7f686606145fe07b4103e269b341d08659d6","target":"record","created_at":"2026-07-05T01:41:21Z","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":"de71e4794cd8390bc3c552c9a50f5ed9042b49cd931a7efe48cb1e8fbbbc031e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T20:45:14Z","title_canon_sha256":"6d4ef244486f1d0d55c841bb29e6e395f97b2fd53df1f3b4f36d9e28f61371d4"},"schema_version":"1.0","source":{"id":"2010.03644","kind":"arxiv","version":1}},"canonical_sha256":"a4d305dd67dc4aaa8360342c450f8b31817e108f6c780f6b53e888541e398391","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4d305dd67dc4aaa8360342c450f8b31817e108f6c780f6b53e888541e398391","first_computed_at":"2026-07-05T01:41:21.553719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:21.553719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c5B/Sc/sEnCcySEpOOM8WJ52w/N//lGBqiQD5AsrGl1HJx9ApFIucZe9tzDMEV8H54okdF3t26I5zV7qVLnBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:21.554076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fa0282eb82453bac56516f9f77a7f686606145fe07b4103e269b341d08659d6","sha256:0057fee222dc5c26eafbf1ff556fe7c36c5903be5db9073b25e126e0ce0c1b52"],"state_sha256":"5ce56bec652538e1a06b1054e8a9dea2f5043f85d6e0ca41b005d33d34fc56b5"}