{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FV36KRSYYJVQJ47U4R7PV7J4OX","short_pith_number":"pith:FV36KRSY","canonical_record":{"source":{"id":"2210.05234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T08:05:18Z","cross_cats_sorted":[],"title_canon_sha256":"17e7ac7896c434d08a7bebaf5345f6ef1f6ece9eaca5e656f36fdce27a0cfea3","abstract_canon_sha256":"6b6cbf7b15774851592522714cb4e2636223cdeec0479c3d92a0f04940148747"},"schema_version":"1.0"},"canonical_sha256":"2d77e54658c26b04f3f4e47efafd3c75f5a213bccc0ceca4ecf9ed70bbc1c472","source":{"kind":"arxiv","id":"2210.05234","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05234","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05234v1","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05234","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"FV36KRSYYJVQ","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"FV36KRSYYJVQJ47U","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"FV36KRSY","created_at":"2026-07-05T05:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FV36KRSYYJVQJ47U4R7PV7J4OX","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T08:05:18Z","cross_cats_sorted":[],"title_canon_sha256":"17e7ac7896c434d08a7bebaf5345f6ef1f6ece9eaca5e656f36fdce27a0cfea3","abstract_canon_sha256":"6b6cbf7b15774851592522714cb4e2636223cdeec0479c3d92a0f04940148747"},"schema_version":"1.0"},"canonical_sha256":"2d77e54658c26b04f3f4e47efafd3c75f5a213bccc0ceca4ecf9ed70bbc1c472","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:14.532938Z","signature_b64":"+xQXjdP86gMcEJ5yixVCVJ7UWdjxPFz0xvRrTaLYgDxBfMNImkC889cTPVZT2GUjESodnJINMOhuIhfTgu0HDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d77e54658c26b04f3f4e47efafd3c75f5a213bccc0ceca4ecf9ed70bbc1c472","last_reissued_at":"2026-07-05T05:05:14.532393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:14.532393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05234","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":"2026-07-05T05:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LpRx4jjSkkPej89PzDl+IrkzZEixDJ1xDJPfXD2l/4LZzPx4fZ78Jdch/cc+OmkBmG9HmhGleZ2d9YuRp3NpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T01:42:34.252560Z"},"content_sha256":"d1eb3a56d877cb7a6430da58c51ddd357d074542aa68074853beb399ffb4ec99","schema_version":"1.0","event_id":"sha256:d1eb3a56d877cb7a6430da58c51ddd357d074542aa68074853beb399ffb4ec99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FV36KRSYYJVQJ47U4R7PV7J4OX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Fu Li, Jingdong Wang, Min Yang, Wenhao Wu, Yuxin Song","submitted_at":"2022-10-11T08:05:18Z","abstract_excerpt":"Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks and superior data efficiency on small datasets. However, temporal relation is not fully exploited by these methods. In this work, we explicitly investigate motion cues in videos as extra prediction target and propose our Masked Appearance-Motion Modeling (MAM2) framework. Specifically, we design an encoder-regressor-decoder pipeline for this task. The regressor separates feature encoding and pretext tasks completion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05234","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/2210.05234/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":"2026-07-05T05:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWGm6WHWBIDpZ24mD/bb6/rYRRAEIQMSUQ+m5ZzXFgdRHS7jxTWGk4UQ05vEWvhrMHsNQbeJGUmfDi2+Rf9bBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T01:42:34.253121Z"},"content_sha256":"6de5491bd94a844e070b6bf537c91e727ae4db8602f5c28dd743f6344ce49cef","schema_version":"1.0","event_id":"sha256:6de5491bd94a844e070b6bf537c91e727ae4db8602f5c28dd743f6344ce49cef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FV36KRSYYJVQJ47U4R7PV7J4OX/bundle.json","state_url":"https://pith.science/pith/FV36KRSYYJVQJ47U4R7PV7J4OX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FV36KRSYYJVQJ47U4R7PV7J4OX/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":"2026-08-03T01:42:34Z","links":{"resolver":"https://pith.science/pith/FV36KRSYYJVQJ47U4R7PV7J4OX","bundle":"https://pith.science/pith/FV36KRSYYJVQJ47U4R7PV7J4OX/bundle.json","state":"https://pith.science/pith/FV36KRSYYJVQJ47U4R7PV7J4OX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FV36KRSYYJVQJ47U4R7PV7J4OX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FV36KRSYYJVQJ47U4R7PV7J4OX","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":"6b6cbf7b15774851592522714cb4e2636223cdeec0479c3d92a0f04940148747","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T08:05:18Z","title_canon_sha256":"17e7ac7896c434d08a7bebaf5345f6ef1f6ece9eaca5e656f36fdce27a0cfea3"},"schema_version":"1.0","source":{"id":"2210.05234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05234","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05234v1","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05234","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"FV36KRSYYJVQ","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"FV36KRSYYJVQJ47U","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"FV36KRSY","created_at":"2026-07-05T05:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:6de5491bd94a844e070b6bf537c91e727ae4db8602f5c28dd743f6344ce49cef","target":"graph","created_at":"2026-07-05T05:05:14Z","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/2210.05234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks and superior data efficiency on small datasets. However, temporal relation is not fully exploited by these methods. In this work, we explicitly investigate motion cues in videos as extra prediction target and propose our Masked Appearance-Motion Modeling (MAM2) framework. Specifically, we design an encoder-regressor-decoder pipeline for this task. The regressor separates feature encoding and pretext tasks completion","authors_text":"Dongliang He, Fu Li, Jingdong Wang, Min Yang, Wenhao Wu, Yuxin Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T08:05:18Z","title":"It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05234","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:d1eb3a56d877cb7a6430da58c51ddd357d074542aa68074853beb399ffb4ec99","target":"record","created_at":"2026-07-05T05:05:14Z","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":"6b6cbf7b15774851592522714cb4e2636223cdeec0479c3d92a0f04940148747","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T08:05:18Z","title_canon_sha256":"17e7ac7896c434d08a7bebaf5345f6ef1f6ece9eaca5e656f36fdce27a0cfea3"},"schema_version":"1.0","source":{"id":"2210.05234","kind":"arxiv","version":1}},"canonical_sha256":"2d77e54658c26b04f3f4e47efafd3c75f5a213bccc0ceca4ecf9ed70bbc1c472","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d77e54658c26b04f3f4e47efafd3c75f5a213bccc0ceca4ecf9ed70bbc1c472","first_computed_at":"2026-07-05T05:05:14.532393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:14.532393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+xQXjdP86gMcEJ5yixVCVJ7UWdjxPFz0xvRrTaLYgDxBfMNImkC889cTPVZT2GUjESodnJINMOhuIhfTgu0HDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:14.532938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1eb3a56d877cb7a6430da58c51ddd357d074542aa68074853beb399ffb4ec99","sha256:6de5491bd94a844e070b6bf537c91e727ae4db8602f5c28dd743f6344ce49cef"],"state_sha256":"d5390abb80c487dc9da953ea012f07c5d2230896c71bc6406260f8b9c235713e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdfXNJXp/Y7J18/YtuEs1qdob2ULQ9bgJMAgxJsOamoN61JaMUw6b6DGOMkBQ8+Ij/VcmnvwQ+Ts6M1RmnRcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T01:42:34.258267Z","bundle_sha256":"b6ce4e2d0dd162622069ce5967b0c4b3dca1314ad3fb3eeef4d7357b7a67104c"}}