{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XS2CLQEWCB3HWP2C75HBPKX4AA","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":"8d8d34da8d6b8d5fa0fe7b2d568543749c150288022d328e78de7ab0f27e177a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:50Z","title_canon_sha256":"f28411df0063f91af0a7db80dcb2b5b56fe37ce53382da224f879c06f048e479"},"schema_version":"1.0","source":{"id":"2402.19479","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19479","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19479v1","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19479","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_12","alias_value":"XS2CLQEWCB3H","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_16","alias_value":"XS2CLQEWCB3HWP2C","created_at":"2026-07-05T07:50:45Z"},{"alias_kind":"pith_short_8","alias_value":"XS2CLQEW","created_at":"2026-07-05T07:50:45Z"}],"graph_snapshots":[{"event_id":"sha256:d4fdd365f84ff3f97f0c667b9038104b46490cefc1ffe566f4aa007a6c077528","target":"graph","created_at":"2026-07-05T07:50:45Z","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/2402.19479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality of the data and annotation upper-bounds the quality of a downstream model. While there exist large text corpora and image-text pairs, high-quality video-text data is much harder to collect. First of all, manual labeling is more time-consuming, as it requires an annotator to watch an entire video. Second, videos have a temporal dimension, consisting of several scenes stacked together, and showing multiple actions. Accordingly, to establish a video dataset with high-quality captions, we propose an automatic approach leveraging multimodal inputs, such as textual video description, sub","authors_text":"Aliaksandr Siarohin, Byung Eun Jeon, Ekaterina Deyneka, Hsiang-wei Chao, Hsin-Ying Lee, Jian Ren, Ming-Hsuan Yang, Sergey Tulyakov, Tsai-Shien Chen, Willi Menapace, Yuwei Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:50Z","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19479","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:c1f20c05ff5da8f20eac878f7e911ef865810bc7877591cd8139fc3bb4f5ddd0","target":"record","created_at":"2026-07-05T07:50:45Z","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":"8d8d34da8d6b8d5fa0fe7b2d568543749c150288022d328e78de7ab0f27e177a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:50Z","title_canon_sha256":"f28411df0063f91af0a7db80dcb2b5b56fe37ce53382da224f879c06f048e479"},"schema_version":"1.0","source":{"id":"2402.19479","kind":"arxiv","version":1}},"canonical_sha256":"bcb425c09610767b3f42ff4e17aafc0019e8c0e46a6f9543e0eb38b84ee1390a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcb425c09610767b3f42ff4e17aafc0019e8c0e46a6f9543e0eb38b84ee1390a","first_computed_at":"2026-07-05T07:50:45.798166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:45.798166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1j7NSozct5xL5JQI9LaBmaOWcBn4ahXQI0UktvfAeNKZy/j/Hki5HYGE7nWQom+z0n5ie75PK33C+Fx9iwCUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:45.798671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19479","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1f20c05ff5da8f20eac878f7e911ef865810bc7877591cd8139fc3bb4f5ddd0","sha256:d4fdd365f84ff3f97f0c667b9038104b46490cefc1ffe566f4aa007a6c077528"],"state_sha256":"831be07e4d6cbe86c7471afbeba53e2a265abcd1f7fd7eae9bfe865c055ec20d"}