{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UYKBNWOXQI3TCK3IPMQ7I4NV7H","short_pith_number":"pith:UYKBNWOX","canonical_record":{"source":{"id":"2405.15160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T02:29:03Z","cross_cats_sorted":[],"title_canon_sha256":"41550f6f515bc80acd07b4bd5fe1dcdd9e6300c8f3dda517654a2d4168c04696","abstract_canon_sha256":"652e94d5c6aac3793f2190f9b09df08ba0d5989275a40702f6eea99603dad925"},"schema_version":"1.0"},"canonical_sha256":"a61416d9d78237312b687b21f471b5f9c60482d613c804f42489ff87c2fc877b","source":{"kind":"arxiv","id":"2405.15160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15160","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15160v1","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15160","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"pith_short_12","alias_value":"UYKBNWOXQI3T","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"pith_short_16","alias_value":"UYKBNWOXQI3TCK3I","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"pith_short_8","alias_value":"UYKBNWOX","created_at":"2026-07-05T08:22:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UYKBNWOXQI3TCK3IPMQ7I4NV7H","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T02:29:03Z","cross_cats_sorted":[],"title_canon_sha256":"41550f6f515bc80acd07b4bd5fe1dcdd9e6300c8f3dda517654a2d4168c04696","abstract_canon_sha256":"652e94d5c6aac3793f2190f9b09df08ba0d5989275a40702f6eea99603dad925"},"schema_version":"1.0"},"canonical_sha256":"a61416d9d78237312b687b21f471b5f9c60482d613c804f42489ff87c2fc877b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:46.030420Z","signature_b64":"4n2YmWMso/7fRC9PUUpWStkEzd/djlRrjzvGEkb0urPiFgGnH7TuDoDNxrjetPX3rBDoUqkS8us9OcI2sjcYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a61416d9d78237312b687b21f471b5f9c60482d613c804f42489ff87c2fc877b","last_reissued_at":"2026-07-05T08:22:46.029919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:46.029919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15160","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:22:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FH5pr5dWEcO6kNCPHiDf2chRp/RdF77vTYf31GObM2agjL8R79bGoEKf/xv+MzgBUJoJMpUYw30v8k+lcqC7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:34:48.281356Z"},"content_sha256":"521f89375e91981c44c5fbb3fdf3deb26d808a91c448e91d9e7e2ee09512bd08","schema_version":"1.0","event_id":"sha256:521f89375e91981c44c5fbb3fdf3deb26d808a91c448e91d9e7e2ee09512bd08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UYKBNWOXQI3TCK3IPMQ7I4NV7H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Chen Wei, Cihang Xie, Hongru Zhu, Sucheng Ren, Yijiang Li","submitted_at":"2024-05-24T02:29:03Z","abstract_excerpt":"This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two key designs are included. First, we organize autoregressive video tokens into clusters that span both spatially and temporally, thereby enabling a richer aggregation of contextual information compared to the standard spatial-only or temporal-only clusters. Second, we adopt a randomized spatiotemporal prediction order to facilitate learning from multi-dimensional data, addressing the limitations of a handcrafted spatia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15160","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/2405.15160/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:22:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+34vd1d+PTgwU9GpNlk6SROf77WHrsN3o+F6471c3ED8xWsffesiLpeYaW2aT7dBUbe2zWfeEBm0FK/+Cn3ICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:34:48.281965Z"},"content_sha256":"e052a94117048987d8ce306e1f1f2f41f725eb305a05804706b27fa03a44a539","schema_version":"1.0","event_id":"sha256:e052a94117048987d8ce306e1f1f2f41f725eb305a05804706b27fa03a44a539"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYKBNWOXQI3TCK3IPMQ7I4NV7H/bundle.json","state_url":"https://pith.science/pith/UYKBNWOXQI3TCK3IPMQ7I4NV7H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYKBNWOXQI3TCK3IPMQ7I4NV7H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T03:34:48Z","links":{"resolver":"https://pith.science/pith/UYKBNWOXQI3TCK3IPMQ7I4NV7H","bundle":"https://pith.science/pith/UYKBNWOXQI3TCK3IPMQ7I4NV7H/bundle.json","state":"https://pith.science/pith/UYKBNWOXQI3TCK3IPMQ7I4NV7H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYKBNWOXQI3TCK3IPMQ7I4NV7H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UYKBNWOXQI3TCK3IPMQ7I4NV7H","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":"652e94d5c6aac3793f2190f9b09df08ba0d5989275a40702f6eea99603dad925","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T02:29:03Z","title_canon_sha256":"41550f6f515bc80acd07b4bd5fe1dcdd9e6300c8f3dda517654a2d4168c04696"},"schema_version":"1.0","source":{"id":"2405.15160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15160","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15160v1","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15160","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"pith_short_12","alias_value":"UYKBNWOXQI3T","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"pith_short_16","alias_value":"UYKBNWOXQI3TCK3I","created_at":"2026-07-05T08:22:46Z"},{"alias_kind":"pith_short_8","alias_value":"UYKBNWOX","created_at":"2026-07-05T08:22:46Z"}],"graph_snapshots":[{"event_id":"sha256:e052a94117048987d8ce306e1f1f2f41f725eb305a05804706b27fa03a44a539","target":"graph","created_at":"2026-07-05T08:22:46Z","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/2405.15160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two key designs are included. First, we organize autoregressive video tokens into clusters that span both spatially and temporally, thereby enabling a richer aggregation of contextual information compared to the standard spatial-only or temporal-only clusters. Second, we adopt a randomized spatiotemporal prediction order to facilitate learning from multi-dimensional data, addressing the limitations of a handcrafted spatia","authors_text":"Alan Yuille, Chen Wei, Cihang Xie, Hongru Zhu, Sucheng Ren, Yijiang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T02:29:03Z","title":"ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15160","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":"sha256:521f89375e91981c44c5fbb3fdf3deb26d808a91c448e91d9e7e2ee09512bd08","target":"record","created_at":"2026-07-05T08:22:46Z","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":"652e94d5c6aac3793f2190f9b09df08ba0d5989275a40702f6eea99603dad925","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T02:29:03Z","title_canon_sha256":"41550f6f515bc80acd07b4bd5fe1dcdd9e6300c8f3dda517654a2d4168c04696"},"schema_version":"1.0","source":{"id":"2405.15160","kind":"arxiv","version":1}},"canonical_sha256":"a61416d9d78237312b687b21f471b5f9c60482d613c804f42489ff87c2fc877b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a61416d9d78237312b687b21f471b5f9c60482d613c804f42489ff87c2fc877b","first_computed_at":"2026-07-05T08:22:46.029919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:46.029919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4n2YmWMso/7fRC9PUUpWStkEzd/djlRrjzvGEkb0urPiFgGnH7TuDoDNxrjetPX3rBDoUqkS8us9OcI2sjcYCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:46.030420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:521f89375e91981c44c5fbb3fdf3deb26d808a91c448e91d9e7e2ee09512bd08","sha256:e052a94117048987d8ce306e1f1f2f41f725eb305a05804706b27fa03a44a539"],"state_sha256":"a66dbcff0aaa699ff2c52a34cbc56edc2780249bc01cf360a87f38a7bdd16de8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FNrOyFnHp8nM3T4M4V9o8QipxsqPG1CmEj+y4UItq4FhVWN2qaaySuviRWoovlaQXWxu6KbO3BIVbarScIt/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:34:48.287333Z","bundle_sha256":"ce75a033ea613c57975edf40c197d157ae6dcfe6a99adaa84ddf31a8e99068a5"}}