{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JTSDYR3KPZBVY77PZ3GKAPJSNP","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":"51c718ab3873d6f0a25ba2d15d9791365ed85fc3116e52b35238067f9b6b58a2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:59:45Z","title_canon_sha256":"cdf38f1a11e85be40e3aaf532b2aba030aabf62512dfa2f9be9ba4f1c7e9dd1e"},"schema_version":"1.0","source":{"id":"2104.11227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.11227","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2104.11227v1","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11227","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"JTSDYR3KPZBV","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"JTSDYR3KPZBVY77P","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"JTSDYR3K","created_at":"2026-07-05T02:34:19Z"}],"graph_snapshots":[{"event_id":"sha256:481ad30a31b5b201a12119321e8ab2ec2826b37bb9774e9367c76abb7024c767","target":"graph","created_at":"2026-07-05T02:34:19Z","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/2104.11227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, ","authors_text":"Bo Xiong, Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:59:45Z","title":"Multiscale Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11227","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:f667816b47fe3e4a9c65300950d733b7a6b4b23dbbe7c47dbab400a4d17fd641","target":"record","created_at":"2026-07-05T02:34:19Z","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":"51c718ab3873d6f0a25ba2d15d9791365ed85fc3116e52b35238067f9b6b58a2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:59:45Z","title_canon_sha256":"cdf38f1a11e85be40e3aaf532b2aba030aabf62512dfa2f9be9ba4f1c7e9dd1e"},"schema_version":"1.0","source":{"id":"2104.11227","kind":"arxiv","version":1}},"canonical_sha256":"4ce43c476a7e435c7fefcecca03d326be6b2e5fe4b4cefaa4d85fba86a369844","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ce43c476a7e435c7fefcecca03d326be6b2e5fe4b4cefaa4d85fba86a369844","first_computed_at":"2026-07-05T02:34:19.008628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:19.008628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aDCDOphtMvr8wAbxn4xuVsW6KphwZKDJUCzjazvcuK0JiiKYaynNkjkzPNj50on7KB+7d0KqOUMuk/RP784LBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:19.009170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.11227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f667816b47fe3e4a9c65300950d733b7a6b4b23dbbe7c47dbab400a4d17fd641","sha256:481ad30a31b5b201a12119321e8ab2ec2826b37bb9774e9367c76abb7024c767"],"state_sha256":"993b3c52c85ccc501155ba0be9e547df1d78fd988f3ba595f089038fb2dbdd79"}