{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LARVTXM4TKKGFU32RCCTRRLTYH","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":"f7f634d2f572be0ff15942aa61b198112ace2baf5a0749bf1145ec27cc66d2d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T12:55:50Z","title_canon_sha256":"b733fb53e233a950c9fdfb5109e838062eb83d30013315e1756b0f25cfe8b33a"},"schema_version":"1.0","source":{"id":"2403.16128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16128","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16128v1","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16128","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"LARVTXM4TKKG","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"LARVTXM4TKKGFU32","created_at":"2026-07-05T08:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"LARVTXM4","created_at":"2026-07-05T08:00:11Z"}],"graph_snapshots":[{"event_id":"sha256:ae76f2db1d42548ad490700e5ea0db45cc84416c5f1625b0258cd8fa128245e6","target":"graph","created_at":"2026-07-05T08:00:11Z","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/2403.16128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Owing to their ability to extract relevant spatio-temporal video embeddings, Vision Transformers (ViTs) are currently the best performing models in video action understanding. However, their generalization over domains or datasets is somewhat limited. In contrast, Visual Language Models (VLMs) have demonstrated exceptional generalization performance, but are currently unable to process videos. Consequently, they cannot extract spatio-temporal patterns that are crucial for action understanding. In this paper, we propose the Four-tiered Prompts (FTP) framework that takes advantage of the complem","authors_text":"Albert Ali Salah, Hui Lu, Hu Jian, Ronald Poppe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T12:55:50Z","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16128","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":"sha256:7f232ab56318af047208799125c914905af919dd0fcdaaa2597efd0781d07854","target":"record","created_at":"2026-07-05T08:00:11Z","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":"f7f634d2f572be0ff15942aa61b198112ace2baf5a0749bf1145ec27cc66d2d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T12:55:50Z","title_canon_sha256":"b733fb53e233a950c9fdfb5109e838062eb83d30013315e1756b0f25cfe8b33a"},"schema_version":"1.0","source":{"id":"2403.16128","kind":"arxiv","version":1}},"canonical_sha256":"582359dd9c9a9462d37a888538c573c1d0613b0248d20efb1eb5f0d72ff28f55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"582359dd9c9a9462d37a888538c573c1d0613b0248d20efb1eb5f0d72ff28f55","first_computed_at":"2026-07-05T08:00:11.010273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:11.010273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y2690aI5Be2W0SEhGEakG58TF7h+aXVq4K1HvnlZq3ypBKShoMG5NlC1dUS+7dtIxg3Jg175XT057AWMFmupDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:11.010686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f232ab56318af047208799125c914905af919dd0fcdaaa2597efd0781d07854","sha256:ae76f2db1d42548ad490700e5ea0db45cc84416c5f1625b0258cd8fa128245e6"],"state_sha256":"4b76513787bd0f03b78509b1877a4dff30f005652ec9b9d266250975a0f6b65a"}