{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5CB5BO4F75AUNQDQLWZO6O7DTB","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":"ceee839dd5da7372d5d3dd3a8197505b837fe35cffc14a382550585fe93b3748","cross_cats_sorted":["cs.IT","cs.LG","eess.IV","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:53Z","title_canon_sha256":"99eebbd271562ee4caa82355fb22d5a6dac8178746362ad6068768b56f20d91f"},"schema_version":"1.0","source":{"id":"2406.07548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07548","created_at":"2026-07-05T08:30:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07548v1","created_at":"2026-07-05T08:30:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07548","created_at":"2026-07-05T08:30:26Z"},{"alias_kind":"pith_short_12","alias_value":"5CB5BO4F75AU","created_at":"2026-07-05T08:30:26Z"},{"alias_kind":"pith_short_16","alias_value":"5CB5BO4F75AUNQDQ","created_at":"2026-07-05T08:30:26Z"},{"alias_kind":"pith_short_8","alias_value":"5CB5BO4F","created_at":"2026-07-05T08:30:26Z"}],"graph_snapshots":[{"event_id":"sha256:c6dbd7c967bd49c13a6170bd2b01306976692bbea5974e5e32c5cc500f408456","target":"graph","created_at":"2026-07-05T08:30:26Z","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/2406.07548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ). BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. BSQ is (1) parameter-efficient without an explicit codebook, (2) scalable to arbitrary token dimensions, and (3) compact: compressing visual data by up to 100$\\times$ with minimal distortion. Our tokenizer uses a transformer encoder and decoder with simple block-wise causal masking to support variable-length videos as input. The resulting BSQ-ViT achieves state-of-the-ar","authors_text":"Philipp Kr\\\"ahenb\\\"uhl, Yuanjun Xiong, Yue Zhao","cross_cats":["cs.IT","cs.LG","eess.IV","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:53Z","title":"Image and Video Tokenization with Binary Spherical Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07548","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":"sha256:16e48e27fa60c55be5741455062366ad89d5ebeef5698a69c705ee3a0d14c88f","target":"record","created_at":"2026-07-05T08:30:26Z","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":"ceee839dd5da7372d5d3dd3a8197505b837fe35cffc14a382550585fe93b3748","cross_cats_sorted":["cs.IT","cs.LG","eess.IV","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:53Z","title_canon_sha256":"99eebbd271562ee4caa82355fb22d5a6dac8178746362ad6068768b56f20d91f"},"schema_version":"1.0","source":{"id":"2406.07548","kind":"arxiv","version":1}},"canonical_sha256":"e883d0bb85ff4146c0705db2ef3be398588ff4fb4741c10705fd29e2885f8b5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e883d0bb85ff4146c0705db2ef3be398588ff4fb4741c10705fd29e2885f8b5c","first_computed_at":"2026-07-05T08:30:26.960930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:26.960930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nOZFeVJSJhm/Wd5Rr6cVZOIY0EafxDj9lPeFllQegrd6KEW00hfkJIkLG4b0HGS/+UT6+3zS6utuCRnLY0rODw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:26.961496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16e48e27fa60c55be5741455062366ad89d5ebeef5698a69c705ee3a0d14c88f","sha256:c6dbd7c967bd49c13a6170bd2b01306976692bbea5974e5e32c5cc500f408456"],"state_sha256":"1f324598792abc74e967743ffc32f27499ac07c56d632f51f9659e2ac2627add"}