{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CGQKBJ3MI5OGEMK7TXZEGZXKJH","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":"d842706c8f5594ff3ebc935c2e8c62b88f8fda72752112a4581b16f8be494775","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T18:52:59Z","title_canon_sha256":"6e76ea88740aa454e40da9d38a6ba9234bbc01a2c14f3219dd4cf0236c256ac1"},"schema_version":"1.0","source":{"id":"2308.09775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09775","created_at":"2026-07-05T06:42:46Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09775v1","created_at":"2026-07-05T06:42:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09775","created_at":"2026-07-05T06:42:46Z"},{"alias_kind":"pith_short_12","alias_value":"CGQKBJ3MI5OG","created_at":"2026-07-05T06:42:46Z"},{"alias_kind":"pith_short_16","alias_value":"CGQKBJ3MI5OGEMK7","created_at":"2026-07-05T06:42:46Z"},{"alias_kind":"pith_short_8","alias_value":"CGQKBJ3M","created_at":"2026-07-05T06:42:46Z"}],"graph_snapshots":[{"event_id":"sha256:1a544b562a48ff53ca3bcec074ef4448f5dfdf90ff2b13bc99906e7639b185aa","target":"graph","created_at":"2026-07-05T06:42:46Z","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/2308.09775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning computer vision models from (and for) movies has a long-standing history. While great progress has been attained, there is still a need for a pretrained multimodal model that can perform well in the ever-growing set of movie understanding tasks the community has been establishing. In this work, we introduce Long-range Multimodal Pretraining, a strategy, and a model that leverages movie data to train transferable multimodal and cross-modal encoders. Our key idea is to learn from all modalities in a movie by observing and extracting relationships over a long-range. After pretraining, we","authors_text":"Dawit Mureja Argaw, Fabian Caba Heilbron, In So Kweon, Joon-Young Lee, Markus Woodson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T18:52:59Z","title":"Long-range Multimodal Pretraining for Movie Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09775","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":"sha256:0e24f2d9868305d616c691cfd126adb0b886f371a70e0f35152b7905b66e69ac","target":"record","created_at":"2026-07-05T06:42:46Z","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":"d842706c8f5594ff3ebc935c2e8c62b88f8fda72752112a4581b16f8be494775","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T18:52:59Z","title_canon_sha256":"6e76ea88740aa454e40da9d38a6ba9234bbc01a2c14f3219dd4cf0236c256ac1"},"schema_version":"1.0","source":{"id":"2308.09775","kind":"arxiv","version":1}},"canonical_sha256":"11a0a0a76c475c62315f9df24366ea49c61f6c9c4a43fbfeba0e508dd2df8678","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11a0a0a76c475c62315f9df24366ea49c61f6c9c4a43fbfeba0e508dd2df8678","first_computed_at":"2026-07-05T06:42:46.680007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:46.680007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JU9qsVMKEUh3Ea41J/zE8n2DPjW09k0/9m+KeyXf2gIxd6LRZ6pSF0uJO+sf/P3KixCTlpoS/TzC/rCXyE8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:46.680523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e24f2d9868305d616c691cfd126adb0b886f371a70e0f35152b7905b66e69ac","sha256:1a544b562a48ff53ca3bcec074ef4448f5dfdf90ff2b13bc99906e7639b185aa"],"state_sha256":"c02e573601727e38802d80a64ad48e184742e07b3b9235213275f0d7502b9f3d"}