{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VGZOM5CAFO7RRM7F22ELY54BVB","short_pith_number":"pith:VGZOM5CA","schema_version":"1.0","canonical_sha256":"a9b2e674402bbf18b3e5d688bc7781a871cd5d1444994b7843ca1e4c64e4c824","source":{"kind":"arxiv","id":"2307.01467","version":1},"attestation_state":"computed","paper":{"title":"Technical Report for Ego4D Long Term Action Anticipation Challenge 2023","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kosuke Ono, Noriyuki Kugo, Tatsuya Ishibashi, Yuji Sato","submitted_at":"2023-07-04T04:12:49Z","abstract_excerpt":"In this report, we describe the technical details of our approach for the Ego4D Long-Term Action Anticipation Challenge 2023. The aim of this task is to predict a sequence of future actions that will take place at an arbitrary time or later, given an input video. To accomplish this task, we introduce three improvements to the baseline model, which consists of an encoder that generates clip-level features from the video, an aggregator that integrates multiple clip-level features, and a decoder that outputs Z future actions. 1) Model ensemble of SlowFast and SlowFast-CLIP; 2) Label smoothing to "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.01467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-04T04:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"f54f8aa1c9d0830f6f36820a8e741dbf9c744146c509780094cf5a9d6f1eab6d","abstract_canon_sha256":"f0996a6c291262285615abce6dae6c9940f2ea4bfd2824d837f599cdef7401a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:56.861467Z","signature_b64":"aln+tM0+adLWa4bXnNjW+Iihr4csyEh1HGCeHE/YiKfNFfrSPkn21lalIF9qCFr4hGZeZjDsOXOYP9UGqIG+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b2e674402bbf18b3e5d688bc7781a871cd5d1444994b7843ca1e4c64e4c824","last_reissued_at":"2026-07-05T06:27:56.861119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:56.861119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Technical Report for Ego4D Long Term Action Anticipation Challenge 2023","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kosuke Ono, Noriyuki Kugo, Tatsuya Ishibashi, Yuji Sato","submitted_at":"2023-07-04T04:12:49Z","abstract_excerpt":"In this report, we describe the technical details of our approach for the Ego4D Long-Term Action Anticipation Challenge 2023. The aim of this task is to predict a sequence of future actions that will take place at an arbitrary time or later, given an input video. To accomplish this task, we introduce three improvements to the baseline model, which consists of an encoder that generates clip-level features from the video, an aggregator that integrates multiple clip-level features, and a decoder that outputs Z future actions. 1) Model ensemble of SlowFast and SlowFast-CLIP; 2) Label smoothing to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01467","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.01467/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.01467","created_at":"2026-07-05T06:27:56.861174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01467v1","created_at":"2026-07-05T06:27:56.861174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01467","created_at":"2026-07-05T06:27:56.861174+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGZOM5CAFO7R","created_at":"2026-07-05T06:27:56.861174+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGZOM5CAFO7RRM7F","created_at":"2026-07-05T06:27:56.861174+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGZOM5CA","created_at":"2026-07-05T06:27:56.861174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00374","citing_title":"Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB","json":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB.json","graph_json":"https://pith.science/api/pith-number/VGZOM5CAFO7RRM7F22ELY54BVB/graph.json","events_json":"https://pith.science/api/pith-number/VGZOM5CAFO7RRM7F22ELY54BVB/events.json","paper":"https://pith.science/paper/VGZOM5CA"},"agent_actions":{"view_html":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB","download_json":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB.json","view_paper":"https://pith.science/paper/VGZOM5CA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01467&json=true","fetch_graph":"https://pith.science/api/pith-number/VGZOM5CAFO7RRM7F22ELY54BVB/graph.json","fetch_events":"https://pith.science/api/pith-number/VGZOM5CAFO7RRM7F22ELY54BVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB/action/storage_attestation","attest_author":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB/action/author_attestation","sign_citation":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB/action/citation_signature","submit_replication":"https://pith.science/pith/VGZOM5CAFO7RRM7F22ELY54BVB/action/replication_record"}},"created_at":"2026-07-05T06:27:56.861174+00:00","updated_at":"2026-07-05T06:27:56.861174+00:00"}