{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AH445RDSG54KILHVLGFNFSSZVQ","short_pith_number":"pith:AH445RDS","canonical_record":{"source":{"id":"2112.01526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"077ff074276839e3ab69963146efb991375fd33896a62de687e6eb297118abe2","abstract_canon_sha256":"032fc6ebda6c57bc58f350c3d4b85e63847b22b5aef05697450c8b4f9517fc6d"},"schema_version":"1.0"},"canonical_sha256":"01f9cec4723778a42cf5598ad2ca59ac3007127e3b91c50481ead67325a369de","source":{"kind":"arxiv","id":"2112.01526","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01526","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01526v2","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01526","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"AH445RDSG54K","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"AH445RDSG54KILHV","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"AH445RDS","created_at":"2026-07-05T04:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AH445RDSG54KILHVLGFNFSSZVQ","target":"record","payload":{"canonical_record":{"source":{"id":"2112.01526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"077ff074276839e3ab69963146efb991375fd33896a62de687e6eb297118abe2","abstract_canon_sha256":"032fc6ebda6c57bc58f350c3d4b85e63847b22b5aef05697450c8b4f9517fc6d"},"schema_version":"1.0"},"canonical_sha256":"01f9cec4723778a42cf5598ad2ca59ac3007127e3b91c50481ead67325a369de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:59.558476Z","signature_b64":"nsWxx4Te5P7Jar9RyvnUHWd8RjWmCPd4pl9woB2Ck+Xe4fc0xm8v75kgsjHAqa+a66zM7Un4aYAMMGByog1cDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01f9cec4723778a42cf5598ad2ca59ac3007127e3b91c50481ead67325a369de","last_reissued_at":"2026-07-05T04:09:59.558031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:59.558031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.01526","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLh4aL2S1qAzcsSjRJfQGDR0tXdQLQgnJtKkp2YNn057rqpFlRnfCtNW7IeDR2lm7/EVSUoDMMa5PGeSzdrDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:22:31.366870Z"},"content_sha256":"8afdc1d98d8be9387adb84cc36b68c186447d9ddd420f6b7d6cc2f80e2a00884","schema_version":"1.0","event_id":"sha256:8afdc1d98d8be9387adb84cc36b68c186447d9ddd420f6b7d6cc2f80e2a00884"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AH445RDSG54KILHVLGFNFSSZVQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Xiong, Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Karttikeya Mangalam, Yanghao Li","submitted_at":"2021-12-02T18:59:57Z","abstract_excerpt":"In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative positional embeddings and residual pooling connections. We instantiate this architecture in five sizes and evaluate it for ImageNet classification, COCO detection and Kinetics video recognition where it outperforms prior work. We further compare MViTv2s' pooling attention to window attention mechanisms where it outperforms the latter in accuracy/compute. Without bel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01526","kind":"arxiv","version":2},"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/2112.01526/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":"2026-07-05T04:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V79fcEVzl2rRHtv4E2N3EUlsQqFlGgfOFcoQdMDm1T+fPMWG1mw0A1TIv0oXargJRyALzuSBKTJsJz7eUyJEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:22:31.367355Z"},"content_sha256":"db46452eabf804b115e54a00e9c42e54a490f83c7a141f189b6907d161cbb5b3","schema_version":"1.0","event_id":"sha256:db46452eabf804b115e54a00e9c42e54a490f83c7a141f189b6907d161cbb5b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AH445RDSG54KILHVLGFNFSSZVQ/bundle.json","state_url":"https://pith.science/pith/AH445RDSG54KILHVLGFNFSSZVQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AH445RDSG54KILHVLGFNFSSZVQ/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":"2026-08-09T22:22:31Z","links":{"resolver":"https://pith.science/pith/AH445RDSG54KILHVLGFNFSSZVQ","bundle":"https://pith.science/pith/AH445RDSG54KILHVLGFNFSSZVQ/bundle.json","state":"https://pith.science/pith/AH445RDSG54KILHVLGFNFSSZVQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AH445RDSG54KILHVLGFNFSSZVQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AH445RDSG54KILHVLGFNFSSZVQ","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":"032fc6ebda6c57bc58f350c3d4b85e63847b22b5aef05697450c8b4f9517fc6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:57Z","title_canon_sha256":"077ff074276839e3ab69963146efb991375fd33896a62de687e6eb297118abe2"},"schema_version":"1.0","source":{"id":"2112.01526","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01526","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01526v2","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01526","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"AH445RDSG54K","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"AH445RDSG54KILHV","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"AH445RDS","created_at":"2026-07-05T04:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:db46452eabf804b115e54a00e9c42e54a490f83c7a141f189b6907d161cbb5b3","target":"graph","created_at":"2026-07-05T04:09:59Z","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/2112.01526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative positional embeddings and residual pooling connections. We instantiate this architecture in five sizes and evaluate it for ImageNet classification, COCO detection and Kinetics video recognition where it outperforms prior work. We further compare MViTv2s' pooling attention to window attention mechanisms where it outperforms the latter in accuracy/compute. Without bel","authors_text":"Bo Xiong, Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Karttikeya Mangalam, Yanghao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:57Z","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01526","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":"sha256:8afdc1d98d8be9387adb84cc36b68c186447d9ddd420f6b7d6cc2f80e2a00884","target":"record","created_at":"2026-07-05T04:09:59Z","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":"032fc6ebda6c57bc58f350c3d4b85e63847b22b5aef05697450c8b4f9517fc6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:57Z","title_canon_sha256":"077ff074276839e3ab69963146efb991375fd33896a62de687e6eb297118abe2"},"schema_version":"1.0","source":{"id":"2112.01526","kind":"arxiv","version":2}},"canonical_sha256":"01f9cec4723778a42cf5598ad2ca59ac3007127e3b91c50481ead67325a369de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01f9cec4723778a42cf5598ad2ca59ac3007127e3b91c50481ead67325a369de","first_computed_at":"2026-07-05T04:09:59.558031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:59.558031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nsWxx4Te5P7Jar9RyvnUHWd8RjWmCPd4pl9woB2Ck+Xe4fc0xm8v75kgsjHAqa+a66zM7Un4aYAMMGByog1cDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:59.558476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01526","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8afdc1d98d8be9387adb84cc36b68c186447d9ddd420f6b7d6cc2f80e2a00884","sha256:db46452eabf804b115e54a00e9c42e54a490f83c7a141f189b6907d161cbb5b3"],"state_sha256":"5c5fdea1fba16f80c466e560b89325818dfb887b5cf69bd835a39462129b7e73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJNYUNtc4xD3Y4NVp6l9xJBy5aYvnruHhjTe1e7CxKkqqpZ6ntXhMp1s/ZjbmFM0X3PG7SdVCgCWOy1S6sv4CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:22:31.371282Z","bundle_sha256":"5e337cd2a8c3418e6b00b26d2109134fb531e60ccf2b236cbed17541854510d7"}}