{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7TQOQ5OBC4LX2532GKAUFB2ZU4","short_pith_number":"pith:7TQOQ5OB","canonical_record":{"source":{"id":"2106.11250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T16:48:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"da5f881019d9d734e5a8deb1af9db4420f59d42c47c81a310dbcc10e93bce62a","abstract_canon_sha256":"4efc897f15da8a41ae500b133770ecbb4007717091aa0ed16f3feb28ef21966a"},"schema_version":"1.0"},"canonical_sha256":"fce0e875c117177d777a3281428759a70d9d0d699621eb03fbdc4b91bf658cdb","source":{"kind":"arxiv","id":"2106.11250","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11250","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11250v1","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11250","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"pith_short_12","alias_value":"7TQOQ5OBC4LX","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"pith_short_16","alias_value":"7TQOQ5OBC4LX2532","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"pith_short_8","alias_value":"7TQOQ5OB","created_at":"2026-07-05T02:50:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7TQOQ5OBC4LX2532GKAUFB2ZU4","target":"record","payload":{"canonical_record":{"source":{"id":"2106.11250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T16:48:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"da5f881019d9d734e5a8deb1af9db4420f59d42c47c81a310dbcc10e93bce62a","abstract_canon_sha256":"4efc897f15da8a41ae500b133770ecbb4007717091aa0ed16f3feb28ef21966a"},"schema_version":"1.0"},"canonical_sha256":"fce0e875c117177d777a3281428759a70d9d0d699621eb03fbdc4b91bf658cdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:58.218486Z","signature_b64":"id9wJVmHmi6vjBTy6yw9BCcw3VBwm7Z5i4c+jAew4hYJZaCsX3ZHNTYF9KdUUtTGzTVRiNi2B7N+yX8DFlRkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fce0e875c117177d777a3281428759a70d9d0d699621eb03fbdc4b91bf658cdb","last_reissued_at":"2026-07-05T02:50:58.218067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:58.218067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.11250","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":"2026-07-05T02:50:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9bf6iQpH639FdWhQJFYewk/GlBeoWIMIR36+VZjQGnwGKVXsx3RjVJ+UZC2N2iP2iWQsl37XPLdb4hZjKS4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:54:54.495390Z"},"content_sha256":"921b3fcb2e494ecdf05f467b95412a05954919fca82de26a8f13e38a83859026","schema_version":"1.0","event_id":"sha256:921b3fcb2e494ecdf05f467b95412a05954919fca82de26a8f13e38a83859026"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7TQOQ5OBC4LX2532GKAUFB2ZU4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Tan, Jie Lei, Mohit Bansal, Thomas Wolf","submitted_at":"2021-06-21T16:48:19Z","abstract_excerpt":"Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task on discretized video tokens generated via VQ-VAE. Unlike language, where the text tokens are more independent, neighboring video tokens typically have strong correlations (e.g., consecutive video frames usually look very similar), and hence uniformly masking individual tokens will make the task too trivial to learn useful representations. To deal with this is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11250","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/2106.11250/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":"2026-07-05T02:50:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HfhCcep5XIMn4AjlMfvCaFu3QuNtDhK47C8efOI9o9rAzsUzZmoohInHUum9Kfraod8xds/O7sCbbq1SU7AvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:54:54.495894Z"},"content_sha256":"1aad6eff9353a26044ca3f84ddc3862b948cb78455f5d98f5dfe03fa4fd47405","schema_version":"1.0","event_id":"sha256:1aad6eff9353a26044ca3f84ddc3862b948cb78455f5d98f5dfe03fa4fd47405"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7TQOQ5OBC4LX2532GKAUFB2ZU4/bundle.json","state_url":"https://pith.science/pith/7TQOQ5OBC4LX2532GKAUFB2ZU4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7TQOQ5OBC4LX2532GKAUFB2ZU4/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":"2026-08-07T00:54:54Z","links":{"resolver":"https://pith.science/pith/7TQOQ5OBC4LX2532GKAUFB2ZU4","bundle":"https://pith.science/pith/7TQOQ5OBC4LX2532GKAUFB2ZU4/bundle.json","state":"https://pith.science/pith/7TQOQ5OBC4LX2532GKAUFB2ZU4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7TQOQ5OBC4LX2532GKAUFB2ZU4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7TQOQ5OBC4LX2532GKAUFB2ZU4","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":"4efc897f15da8a41ae500b133770ecbb4007717091aa0ed16f3feb28ef21966a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T16:48:19Z","title_canon_sha256":"da5f881019d9d734e5a8deb1af9db4420f59d42c47c81a310dbcc10e93bce62a"},"schema_version":"1.0","source":{"id":"2106.11250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11250","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11250v1","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11250","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"pith_short_12","alias_value":"7TQOQ5OBC4LX","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"pith_short_16","alias_value":"7TQOQ5OBC4LX2532","created_at":"2026-07-05T02:50:58Z"},{"alias_kind":"pith_short_8","alias_value":"7TQOQ5OB","created_at":"2026-07-05T02:50:58Z"}],"graph_snapshots":[{"event_id":"sha256:1aad6eff9353a26044ca3f84ddc3862b948cb78455f5d98f5dfe03fa4fd47405","target":"graph","created_at":"2026-07-05T02:50:58Z","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/2106.11250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task on discretized video tokens generated via VQ-VAE. Unlike language, where the text tokens are more independent, neighboring video tokens typically have strong correlations (e.g., consecutive video frames usually look very similar), and hence uniformly masking individual tokens will make the task too trivial to learn useful representations. To deal with this is","authors_text":"Hao Tan, Jie Lei, Mohit Bansal, Thomas Wolf","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T16:48:19Z","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11250","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":"sha256:921b3fcb2e494ecdf05f467b95412a05954919fca82de26a8f13e38a83859026","target":"record","created_at":"2026-07-05T02:50:58Z","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":"4efc897f15da8a41ae500b133770ecbb4007717091aa0ed16f3feb28ef21966a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T16:48:19Z","title_canon_sha256":"da5f881019d9d734e5a8deb1af9db4420f59d42c47c81a310dbcc10e93bce62a"},"schema_version":"1.0","source":{"id":"2106.11250","kind":"arxiv","version":1}},"canonical_sha256":"fce0e875c117177d777a3281428759a70d9d0d699621eb03fbdc4b91bf658cdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fce0e875c117177d777a3281428759a70d9d0d699621eb03fbdc4b91bf658cdb","first_computed_at":"2026-07-05T02:50:58.218067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:58.218067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"id9wJVmHmi6vjBTy6yw9BCcw3VBwm7Z5i4c+jAew4hYJZaCsX3ZHNTYF9KdUUtTGzTVRiNi2B7N+yX8DFlRkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:58.218486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:921b3fcb2e494ecdf05f467b95412a05954919fca82de26a8f13e38a83859026","sha256:1aad6eff9353a26044ca3f84ddc3862b948cb78455f5d98f5dfe03fa4fd47405"],"state_sha256":"eb35adac451f0d64d2c70be0b21a78a57c42ec4d901f05c034c4f13a5647d631"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QKuB5uSFpBn4/xCr2ggp0mVfOk+hvx2FupgqpnSW/7lK3IIoEnYd659ZK4hyUt07nD4JUqP3swssyWkV92h1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:54:54.505345Z","bundle_sha256":"80a7efe8032989ea01200b9cbd70d28833676fa34cc32c092d7f2565d4a93419"}}