{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FVQKR2P6WAPUXII3KINHENZHWI","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":"517819361ca5a812ec648b256e8e116bf724001a25f396b0e62fc532c787bdfd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-01T17:57:28Z","title_canon_sha256":"eb3295ba597f3cb013954cf1e7161c2af7433fbafab1c42ba13f6a87fb35800a"},"schema_version":"1.0","source":{"id":"2207.00579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00579","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00579v1","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00579","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"FVQKR2P6WAPU","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"FVQKR2P6WAPUXII3","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"FVQKR2P6","created_at":"2026-07-05T04:36:44Z"}],"graph_snapshots":[{"event_id":"sha256:5687af46880eac1161e5d46f93910242889169fd828c26d65063d176daf18e07","target":"graph","created_at":"2026-07-05T04:36:44Z","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/2207.00579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-text model: CLIP and a video encoder Slowfast network. The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames. We show that the features obtained from both encoders are complementary to each other, thus outperforming the baseline on Ego4D for the task of long-term action ant","authors_text":"Michael S. Ryoo, Srijan Das","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-01T17:57:28Z","title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00579","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:ecac459e8077c1a5c9f62fb4937be648336b9d47e70ece0e620376acbbaaa323","target":"record","created_at":"2026-07-05T04:36:44Z","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":"517819361ca5a812ec648b256e8e116bf724001a25f396b0e62fc532c787bdfd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-01T17:57:28Z","title_canon_sha256":"eb3295ba597f3cb013954cf1e7161c2af7433fbafab1c42ba13f6a87fb35800a"},"schema_version":"1.0","source":{"id":"2207.00579","kind":"arxiv","version":1}},"canonical_sha256":"2d60a8e9feb01f4ba11b521a723727b217b785253cfda343c2adda388382d15e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d60a8e9feb01f4ba11b521a723727b217b785253cfda343c2adda388382d15e","first_computed_at":"2026-07-05T04:36:44.695975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:44.695975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/qqSZrlniPKgYghnRn1fF7/AWA4MwrZVvzf2yjuSoqcJH320jJr+12qJ8hsUx2HF4cWftk6ZoC5Z5yKGqP1YCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:44.696434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecac459e8077c1a5c9f62fb4937be648336b9d47e70ece0e620376acbbaaa323","sha256:5687af46880eac1161e5d46f93910242889169fd828c26d65063d176daf18e07"],"state_sha256":"f6a2635892d223aa2d901e01b369edbad069b859e9729992965f979c69a885e2"}