{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M2AWXZV5A4GDASSSABPRZMFVV4","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":"2bc759c62123890f9482b794f072a99663829c3fdafc505cbc6f6b24e2e1a7df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-13T03:50:07Z","title_canon_sha256":"77a8a8afac5d28c0076973e2b09d645f2ffd41101ffe5583455942b2d30d2a9d"},"schema_version":"1.0","source":{"id":"2110.06476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06476","created_at":"2026-07-05T03:22:26Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06476v1","created_at":"2026-07-05T03:22:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06476","created_at":"2026-07-05T03:22:26Z"},{"alias_kind":"pith_short_12","alias_value":"M2AWXZV5A4GD","created_at":"2026-07-05T03:22:26Z"},{"alias_kind":"pith_short_16","alias_value":"M2AWXZV5A4GDASSS","created_at":"2026-07-05T03:22:26Z"},{"alias_kind":"pith_short_8","alias_value":"M2AWXZV5","created_at":"2026-07-05T03:22:26Z"}],"graph_snapshots":[{"event_id":"sha256:dfd425a0bab12071d891475f8b8630ba5e0400da3159b71dab381b7b272d6bd8","target":"graph","created_at":"2026-07-05T03:22:26Z","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/2110.06476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The VALUE (Video-And-Language Understanding Evaluation) benchmark is newly introduced to evaluate and analyze multi-modal representation learning algorithms on three video-and-language tasks: Retrieval, QA, and Captioning. The main objective of the VALUE challenge is to train a task-agnostic model that is simultaneously applicable for various tasks with different characteristics. This technical report describes our winning strategies for the VALUE challenge: 1) single model optimization, 2) transfer learning with visual concepts, and 3) task-aware ensemble. The first and third strategies are d","authors_text":"Eun-Sol Kim, Gunsoo Han, Jonghwan Mun, Kyoung-Woon On, Minchul Shin, Woo-Young Kang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-13T03:50:07Z","title":"Winning the ICCV'2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06476","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":"sha256:7546482d620c86336eb213c893ed04c647c0973b2d84394d31e47665d61e458f","target":"record","created_at":"2026-07-05T03:22:26Z","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":"2bc759c62123890f9482b794f072a99663829c3fdafc505cbc6f6b24e2e1a7df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-13T03:50:07Z","title_canon_sha256":"77a8a8afac5d28c0076973e2b09d645f2ffd41101ffe5583455942b2d30d2a9d"},"schema_version":"1.0","source":{"id":"2110.06476","kind":"arxiv","version":1}},"canonical_sha256":"66816be6bd070c304a52005f1cb0b5af3fb14dbd2ab03a68ec5416c865dffb88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66816be6bd070c304a52005f1cb0b5af3fb14dbd2ab03a68ec5416c865dffb88","first_computed_at":"2026-07-05T03:22:26.383195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:26.383195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7NedO9nmaOcx1Ko2mQY0r8oiuAU+JaCbvmMbjtN7jBWaw8Blt63COCTV2cfHgoxkl6N37pEYTU2qjZeVatsIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:26.383616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7546482d620c86336eb213c893ed04c647c0973b2d84394d31e47665d61e458f","sha256:dfd425a0bab12071d891475f8b8630ba5e0400da3159b71dab381b7b272d6bd8"],"state_sha256":"668478c38ee8fc2dcd8d830de12f018858324b442c445ed0232c524e93a2a70b"}