{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A4QSUGFH3V7CJUP5EUGDR3UTGF","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":"5b6ab4b06f554da013ea70a15551d8d5a41900ca3509ba6598338f3259688f79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-04T09:14:18Z","title_canon_sha256":"c20d6b5db0d49d66e317f0bce431ae1c8c08b8124047a8401ce95c70370d9e90"},"schema_version":"1.0","source":{"id":"2302.02136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02136","created_at":"2026-07-05T05:48:05Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02136v2","created_at":"2026-07-05T05:48:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02136","created_at":"2026-07-05T05:48:05Z"},{"alias_kind":"pith_short_12","alias_value":"A4QSUGFH3V7C","created_at":"2026-07-05T05:48:05Z"},{"alias_kind":"pith_short_16","alias_value":"A4QSUGFH3V7CJUP5","created_at":"2026-07-05T05:48:05Z"},{"alias_kind":"pith_short_8","alias_value":"A4QSUGFH","created_at":"2026-07-05T05:48:05Z"}],"graph_snapshots":[{"event_id":"sha256:ba0ee109d2469eca7dc64be8e50ace5808a0a273956eecc2bd57caa1e60b8ffc","target":"graph","created_at":"2026-07-05T05:48:05Z","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/2302.02136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer (PMT) model, which simply incorporates a learnable word embedding layer, a few convolutional and transformer layers. We use the anisotropic pyramid to fulfill video-language interactions across different spatio-temporal scales. In addition to the canonical pyramid, which includes both bottom-up and top-down pathways with lateral connections, novel strategies a","authors_text":"Chongyang Wang, Min Peng, Xiang-Dong Zhou, Yu Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-04T09:14:18Z","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02136","kind":"arxiv","version":2},"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":"sha256:4f45ae4d643147932810de3eda2822b135b513e6da1019617ae81934ea1af103","target":"record","created_at":"2026-07-05T05:48:05Z","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":"5b6ab4b06f554da013ea70a15551d8d5a41900ca3509ba6598338f3259688f79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-04T09:14:18Z","title_canon_sha256":"c20d6b5db0d49d66e317f0bce431ae1c8c08b8124047a8401ce95c70370d9e90"},"schema_version":"1.0","source":{"id":"2302.02136","kind":"arxiv","version":2}},"canonical_sha256":"07212a18a7dd7e24d1fd250c38ee933179fd352ea5db745172a0a2f6c7c62877","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07212a18a7dd7e24d1fd250c38ee933179fd352ea5db745172a0a2f6c7c62877","first_computed_at":"2026-07-05T05:48:05.742621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:05.742621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zHqmFlta90ZqLLKDqMFFiQ2je4aPO7FPOYAQdy92rPBloLPYj90c04tUBNo/n+HaPVAXiXrW4xD2+4uRiotgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:05.743060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f45ae4d643147932810de3eda2822b135b513e6da1019617ae81934ea1af103","sha256:ba0ee109d2469eca7dc64be8e50ace5808a0a273956eecc2bd57caa1e60b8ffc"],"state_sha256":"a37b6c1e0cac7295bb3814f51f2440ca87b3519b42ddcbd860bbd755fd9052e5"}