{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MZYFFLJYSAY3TZ43MEO2TDZBC3","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":"9285f5efcb89e554eb0558c1d2f89ec12792b60786b5f3206ce542639d3f5ddd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T04:27:06Z","title_canon_sha256":"5ec3b3a93bd51a95b7ec14b710e049b15cd1bbc22b9023f451dbdc1f9fef7e3d"},"schema_version":"1.0","source":{"id":"2407.07356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07356","created_at":"2026-07-05T10:34:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07356v2","created_at":"2026-07-05T10:34:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07356","created_at":"2026-07-05T10:34:38Z"},{"alias_kind":"pith_short_12","alias_value":"MZYFFLJYSAY3","created_at":"2026-07-05T10:34:38Z"},{"alias_kind":"pith_short_16","alias_value":"MZYFFLJYSAY3TZ43","created_at":"2026-07-05T10:34:38Z"},{"alias_kind":"pith_short_8","alias_value":"MZYFFLJY","created_at":"2026-07-05T10:34:38Z"}],"graph_snapshots":[{"event_id":"sha256:ed996b8984ce98ca6672852a848059d4d70f56b0dc457eefe4d736a39b8123dd","target":"graph","created_at":"2026-07-05T10:34:38Z","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/2407.07356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual signals as a new interface for models to interact with the environment. Specifically, we choose videos as a representative visual signal. And by training autoregressive Transformers on video datasets in a self-supervised objective, we find that the model emerges a zero-shot capability to infer the semantics from a demonstration video, and imitate the semantics to an unseen scenario. This allows the models to perform unse","authors_text":"Jiang Bian, Junliang Guo, Linli Xu, Li Zhao, Tianyu He, Wentao Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T04:27:06Z","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07356","kind":"arxiv","version":2},"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":"sha256:1c7d1887812fa06228fe1b984ca1a2ca8f939636fe8312bb3bdea1c52ce0b4fa","target":"record","created_at":"2026-07-05T10:34:38Z","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":"9285f5efcb89e554eb0558c1d2f89ec12792b60786b5f3206ce542639d3f5ddd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T04:27:06Z","title_canon_sha256":"5ec3b3a93bd51a95b7ec14b710e049b15cd1bbc22b9023f451dbdc1f9fef7e3d"},"schema_version":"1.0","source":{"id":"2407.07356","kind":"arxiv","version":2}},"canonical_sha256":"667052ad389031b9e79b611da98f2116d09dbd8106a636ca14df91ddcad1d35a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"667052ad389031b9e79b611da98f2116d09dbd8106a636ca14df91ddcad1d35a","first_computed_at":"2026-07-05T10:34:38.681421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:38.681421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uTUBw46N0qGqqyUfCGguiwduOsmdQswhPXtfTq48Aoas/CPI7p7RidyIW3ET+p4OcSDb98ludrs1YJS4w7mUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:38.682043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c7d1887812fa06228fe1b984ca1a2ca8f939636fe8312bb3bdea1c52ce0b4fa","sha256:ed996b8984ce98ca6672852a848059d4d70f56b0dc457eefe4d736a39b8123dd"],"state_sha256":"cd88ce4b4c3fe7cd32fce3e8eb2fca60d8fcfd28db1261191deed437976ac922"}