{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Y3JUZ5CDFKCQBIYV6OWIJIFZFN","short_pith_number":"pith:Y3JUZ5CD","canonical_record":{"source":{"id":"2201.05991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-16T07:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"7e225b4d05b251f0d7b5a4ee4a3c070d7f2ef44c10ce27baa0b6459055e08212","abstract_canon_sha256":"e78aa3760ac89d79e62a4c7d76536ae8c814e9685d8fceaf17695900d3031a64"},"schema_version":"1.0"},"canonical_sha256":"c6d34cf4432a8500a315f3ac84a0b92b7d2b7cd1558f9a56f68cf34600e67069","source":{"kind":"arxiv","id":"2201.05991","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05991","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05991v3","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05991","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y3JUZ5CDFKCQ","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y3JUZ5CDFKCQBIYV","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y3JUZ5CD","created_at":"2026-07-05T05:40:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Y3JUZ5CDFKCQBIYV6OWIJIFZFN","target":"record","payload":{"canonical_record":{"source":{"id":"2201.05991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-16T07:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"7e225b4d05b251f0d7b5a4ee4a3c070d7f2ef44c10ce27baa0b6459055e08212","abstract_canon_sha256":"e78aa3760ac89d79e62a4c7d76536ae8c814e9685d8fceaf17695900d3031a64"},"schema_version":"1.0"},"canonical_sha256":"c6d34cf4432a8500a315f3ac84a0b92b7d2b7cd1558f9a56f68cf34600e67069","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:44.585993Z","signature_b64":"BWSG/0DfwqOMJ7sRR3IPwX001V1zWGR/W8TpUbE57Xe5fPBZ06w5a1NoKKrB0gtK0QDbnhZpANJvpNvS2CjKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d34cf4432a8500a315f3ac84a0b92b7d2b7cd1558f9a56f68cf34600e67069","last_reissued_at":"2026-07-05T05:40:44.585503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:44.585503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.05991","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:40:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izw+Tubd6Qrmy4Vs489dVgjIY9Cwy+bCtXU0Pic5U7Nx3pp3iU2SX41Q/YcW2uw242ES+c5WvzAo6H1K3EzOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:59:10.243874Z"},"content_sha256":"3dca706362712f892d59760958ad304b395189185fbcd78e6d3b612caaea06b0","schema_version":"1.0","event_id":"sha256:3dca706362712f892d59760958ad304b395189185fbcd78e6d3b612caaea06b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Y3JUZ5CDFKCQBIYV6OWIJIFZFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Transformers: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Clap\\'es, Anders S. Johansen, Javier Selva, Kamal Nasrollahi, Sergio Escalera, Thomas B. Moeslund","submitted_at":"2022-01-16T07:31:55Z","abstract_excerpt":"Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05991","kind":"arxiv","version":3},"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/2201.05991/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":"2026-07-05T05:40:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IJhoKe817fCU6jeuHaYS0J6E/aRG9YngJEfD0mmrdfr/g8T1VSxV+qzsnb9kGKnfqsShm89485NB/uTM9Q7OCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:59:10.244963Z"},"content_sha256":"cea3fe4f60e256d3d27edfdc0dda7884f44e379d70503ecbfdc55cac84bf6345","schema_version":"1.0","event_id":"sha256:cea3fe4f60e256d3d27edfdc0dda7884f44e379d70503ecbfdc55cac84bf6345"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/bundle.json","state_url":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/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":"2026-08-08T14:59:10Z","links":{"resolver":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN","bundle":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/bundle.json","state":"https://pith.science/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3JUZ5CDFKCQBIYV6OWIJIFZFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Y3JUZ5CDFKCQBIYV6OWIJIFZFN","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":"e78aa3760ac89d79e62a4c7d76536ae8c814e9685d8fceaf17695900d3031a64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-16T07:31:55Z","title_canon_sha256":"7e225b4d05b251f0d7b5a4ee4a3c070d7f2ef44c10ce27baa0b6459055e08212"},"schema_version":"1.0","source":{"id":"2201.05991","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05991","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05991v3","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05991","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y3JUZ5CDFKCQ","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y3JUZ5CDFKCQBIYV","created_at":"2026-07-05T05:40:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y3JUZ5CD","created_at":"2026-07-05T05:40:44Z"}],"graph_snapshots":[{"event_id":"sha256:cea3fe4f60e256d3d27edfdc0dda7884f44e379d70503ecbfdc55cac84bf6345","target":"graph","created_at":"2026-07-05T05:40:44Z","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/2201.05991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve in","authors_text":"Albert Clap\\'es, Anders S. Johansen, Javier Selva, Kamal Nasrollahi, Sergio Escalera, Thomas B. Moeslund","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-16T07:31:55Z","title":"Video Transformers: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05991","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":"sha256:3dca706362712f892d59760958ad304b395189185fbcd78e6d3b612caaea06b0","target":"record","created_at":"2026-07-05T05:40:44Z","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":"e78aa3760ac89d79e62a4c7d76536ae8c814e9685d8fceaf17695900d3031a64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-16T07:31:55Z","title_canon_sha256":"7e225b4d05b251f0d7b5a4ee4a3c070d7f2ef44c10ce27baa0b6459055e08212"},"schema_version":"1.0","source":{"id":"2201.05991","kind":"arxiv","version":3}},"canonical_sha256":"c6d34cf4432a8500a315f3ac84a0b92b7d2b7cd1558f9a56f68cf34600e67069","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6d34cf4432a8500a315f3ac84a0b92b7d2b7cd1558f9a56f68cf34600e67069","first_computed_at":"2026-07-05T05:40:44.585503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:44.585503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BWSG/0DfwqOMJ7sRR3IPwX001V1zWGR/W8TpUbE57Xe5fPBZ06w5a1NoKKrB0gtK0QDbnhZpANJvpNvS2CjKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:44.585993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05991","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dca706362712f892d59760958ad304b395189185fbcd78e6d3b612caaea06b0","sha256:cea3fe4f60e256d3d27edfdc0dda7884f44e379d70503ecbfdc55cac84bf6345"],"state_sha256":"7e9c62c30d6bd53cb8004327c0d2ef5a377d9710afec0974112db67e619832a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hOAFI7rcABdWjzxzYgfZ9nuatQjb8s/As4tubHEGmtCbikqSSJkO6xgnC+k4chJxJU2pXwMlKKVaSNQ0Fh3ECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:59:10.251327Z","bundle_sha256":"6a42b30f067a9d8697a2102fd7a0a47bf8fcba45b6733741e7ec6ba5b2383801"}}