{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GYHHUY2RECW6FVX6BIUK77QT3Q","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":"b141ebc1111e41aa002585526d21fce331887cde8a19365685acd877e05ae4cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T02:14:19Z","title_canon_sha256":"b3932c50818312193a6ffcd7345c9fcc91802777c785d6a2fea68c0d80a8aa12"},"schema_version":"1.0","source":{"id":"2307.16368","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16368","created_at":"2026-07-05T08:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16368v3","created_at":"2026-07-05T08:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16368","created_at":"2026-07-05T08:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"GYHHUY2RECW6","created_at":"2026-07-05T08:02:45Z"},{"alias_kind":"pith_short_16","alias_value":"GYHHUY2RECW6FVX6","created_at":"2026-07-05T08:02:45Z"},{"alias_kind":"pith_short_8","alias_value":"GYHHUY2R","created_at":"2026-07-05T08:02:45Z"}],"graph_snapshots":[{"event_id":"sha256:f593471b598dd29b3e9a64c62de07bc27626e79f3a686b7c919c82a93a036174","target":"graph","created_at":"2026-07-05T08:02:45Z","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/2307.16368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can we better anticipate an actor's future actions (e.g. mix eggs) by knowing what commonly happens after his/her current action (e.g. crack eggs)? What if we also know the longer-term goal of the actor (e.g. making egg fried rice)? The long-term action anticipation (LTA) task aims to predict an actor's future behavior from video observations in the form of verb and noun sequences, and it is crucial for human-machine interaction. We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a ","authors_text":"Ce Zhang, Changcheng Fu, Chen Sun, Kwonjoon Lee, Minh Quan Do, Nakul Agarwal, Qi Zhao, Shijie Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T02:14:19Z","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16368","kind":"arxiv","version":3},"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":"sha256:3e5f4232390c548f55c2ac3013dfa792f9916447268e8f18bbb001f304f72568","target":"record","created_at":"2026-07-05T08:02:45Z","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":"b141ebc1111e41aa002585526d21fce331887cde8a19365685acd877e05ae4cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T02:14:19Z","title_canon_sha256":"b3932c50818312193a6ffcd7345c9fcc91802777c785d6a2fea68c0d80a8aa12"},"schema_version":"1.0","source":{"id":"2307.16368","kind":"arxiv","version":3}},"canonical_sha256":"360e7a635120ade2d6fe0a28affe13dc218b0e881b236a132ab043e48de56896","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"360e7a635120ade2d6fe0a28affe13dc218b0e881b236a132ab043e48de56896","first_computed_at":"2026-07-05T08:02:45.131742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:45.131742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lThfSyfpAYuCwclWJzrZEevk33rd+S4BB5mw7khLFiNwBp3tYt0PcOZtHYekYkM4Ds7uKxSJtstUNb9VbGkyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:45.132195Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16368","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e5f4232390c548f55c2ac3013dfa792f9916447268e8f18bbb001f304f72568","sha256:f593471b598dd29b3e9a64c62de07bc27626e79f3a686b7c919c82a93a036174"],"state_sha256":"b363259833a7b83b64e12ba70da9e94e1c6a85ed72b03710d1f5853c5c7b51ed"}