{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5CB5BO4F75AUNQDQLWZO6O7DTB","short_pith_number":"pith:5CB5BO4F","schema_version":"1.0","canonical_sha256":"e883d0bb85ff4146c0705db2ef3be398588ff4fb4741c10705fd29e2885f8b5c","source":{"kind":"arxiv","id":"2406.07548","version":1},"attestation_state":"computed","paper":{"title":"Image and Video Tokenization with Binary Spherical Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","eess.IV","math.IT"],"primary_cat":"cs.CV","authors_text":"Philipp Kr\\\"ahenb\\\"uhl, Yuanjun Xiong, Yue Zhao","submitted_at":"2024-06-11T17:59:53Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.07548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:53Z","cross_cats_sorted":["cs.IT","cs.LG","eess.IV","math.IT"],"title_canon_sha256":"99eebbd271562ee4caa82355fb22d5a6dac8178746362ad6068768b56f20d91f","abstract_canon_sha256":"ceee839dd5da7372d5d3dd3a8197505b837fe35cffc14a382550585fe93b3748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:26.961496Z","signature_b64":"nOZFeVJSJhm/Wd5Rr6cVZOIY0EafxDj9lPeFllQegrd6KEW00hfkJIkLG4b0HGS/+UT6+3zS6utuCRnLY0rODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e883d0bb85ff4146c0705db2ef3be398588ff4fb4741c10705fd29e2885f8b5c","last_reissued_at":"2026-07-05T08:30:26.960930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:26.960930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image and Video Tokenization with Binary Spherical Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","eess.IV","math.IT"],"primary_cat":"cs.CV","authors_text":"Philipp Kr\\\"ahenb\\\"uhl, Yuanjun Xiong, Yue Zhao","submitted_at":"2024-06-11T17:59:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07548","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/2406.07548/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.07548","created_at":"2026-07-05T08:30:26.960993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07548v1","created_at":"2026-07-05T08:30:26.960993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07548","created_at":"2026-07-05T08:30:26.960993+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CB5BO4F75AU","created_at":"2026-07-05T08:30:26.960993+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CB5BO4F75AUNQDQ","created_at":"2026-07-05T08:30:26.960993+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CB5BO4F","created_at":"2026-07-05T08:30:26.960993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25548","citing_title":"Concept Removal for Frontier Image Generative Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04461","citing_title":"ChannelTok: Efficient Flexible-Length Vision Tokenization","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":204,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30317","citing_title":"VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19750","citing_title":"CPC-VAR:Continual Personalized and Compositional Generation in Visual Autoregressive Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22394","citing_title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11704","citing_title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00265","citing_title":"Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13030","citing_title":"Generative Refinement Networks for Visual Synthesis","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07915","citing_title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":248,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05171","citing_title":"Modality-Aware and Anatomical Vector-Quantized Autoencoding for Multimodal Brain MRI","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB","json":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB.json","graph_json":"https://pith.science/api/pith-number/5CB5BO4F75AUNQDQLWZO6O7DTB/graph.json","events_json":"https://pith.science/api/pith-number/5CB5BO4F75AUNQDQLWZO6O7DTB/events.json","paper":"https://pith.science/paper/5CB5BO4F"},"agent_actions":{"view_html":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB","download_json":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB.json","view_paper":"https://pith.science/paper/5CB5BO4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07548&json=true","fetch_graph":"https://pith.science/api/pith-number/5CB5BO4F75AUNQDQLWZO6O7DTB/graph.json","fetch_events":"https://pith.science/api/pith-number/5CB5BO4F75AUNQDQLWZO6O7DTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB/action/storage_attestation","attest_author":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB/action/author_attestation","sign_citation":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB/action/citation_signature","submit_replication":"https://pith.science/pith/5CB5BO4F75AUNQDQLWZO6O7DTB/action/replication_record"}},"created_at":"2026-07-05T08:30:26.960993+00:00","updated_at":"2026-07-05T08:30:26.960993+00:00"}