{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OVGGFHSGBUWC2XS7EZVLJFT2JW","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":"472616795688543ad1c6b9615e56aa2d632c0952b70bd30f5aa6ed366f90d8cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-18T04:20:33Z","title_canon_sha256":"cc6c847ff5ba83d063be5344c41c7ab69e6924ffb91c5c9b37e6b70ff87c0e4d"},"schema_version":"1.0","source":{"id":"2201.06734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06734","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06734v1","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06734","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"OVGGFHSGBUWC","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"OVGGFHSGBUWC2XS7","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"OVGGFHSG","created_at":"2026-07-05T03:49:00Z"}],"graph_snapshots":[{"event_id":"sha256:f1ef34121373c4688282239ae66f13975a242002e3e95bb61dce7525368b4017","target":"graph","created_at":"2026-07-05T03:49:00Z","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/2201.06734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we aim to predict the plausible future action steps given an observation of the past and study the task of instructional activity anticipation. Unlike previous anticipation tasks that aim at action label prediction, our work targets at generating natural language outputs that provide interpretable and accurate descriptions of future action steps. It is a challenging task due to the lack of semantic information extracted from the instructional videos. To overcome this challenge, we propose a novel knowledge distillation framework to exploit the related external textual knowledge ","authors_text":"Chenliang Xu, Jiebo Luo, Jingen Liu, Jing Huang, Tao Mei, Xiaodong He, Zhengyuan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-18T04:20:33Z","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06734","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":"sha256:9d36bc0443a68ee7133f6c63559e26d4f9b944d1b6d5704d6a2f39e94d7acc70","target":"record","created_at":"2026-07-05T03:49:00Z","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":"472616795688543ad1c6b9615e56aa2d632c0952b70bd30f5aa6ed366f90d8cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-18T04:20:33Z","title_canon_sha256":"cc6c847ff5ba83d063be5344c41c7ab69e6924ffb91c5c9b37e6b70ff87c0e4d"},"schema_version":"1.0","source":{"id":"2201.06734","kind":"arxiv","version":1}},"canonical_sha256":"754c629e460d2c2d5e5f266ab4967a4dbb1a471aebaf345a51d37923e10c5573","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"754c629e460d2c2d5e5f266ab4967a4dbb1a471aebaf345a51d37923e10c5573","first_computed_at":"2026-07-05T03:49:00.936258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:49:00.936258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c6mA4o8M6JC8AkEmboJkISFu1m2nrMccEXEb2EUGRZ3PMfiyiMLSOfDLvmfrM0RgPJhGhKBCM17zZwDzAuosAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:49:00.936647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.06734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d36bc0443a68ee7133f6c63559e26d4f9b944d1b6d5704d6a2f39e94d7acc70","sha256:f1ef34121373c4688282239ae66f13975a242002e3e95bb61dce7525368b4017"],"state_sha256":"31deaaa417f16ad7d7d866493030f7381e3e0039df8dfd30c9f74b336b98893b"}