{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HOI2SLEZXSS3QIOFXDPHYFLBLA","short_pith_number":"pith:HOI2SLEZ","schema_version":"1.0","canonical_sha256":"3b91a92c99bca5b821c5b8de7c1561582cd0c96a893d33ee9020af6473361529","source":{"kind":"arxiv","id":"2411.10281","version":1},"attestation_state":"computed","paper":{"title":"Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gregor Kobsik, Isaak Lim, Julius Nehring-Wirxel, Leif Kobbelt, Paula Usinger, Tim Elsner, Victor Czech, Yanjiang He","submitted_at":"2024-11-15T15:36:48Z","abstract_excerpt":"In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the context of images, tokenisation of visual data is usually limited to regular grids obtained from quantisation methods, without global content awareness. Our work improves tokenisation of visual data by bringing Byte Pair Encoding from 1D to multiple dimensions, as a complementary add-on to existing compression. We achieve this through counting constellations of to"},"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":"2411.10281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T15:36:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5a5a74c20777394462f69f7affc20c86603bf76a1e03c9c9fc9b453380f49b3d","abstract_canon_sha256":"234e47aa41c8ad286923b68e0615ef575214e7bf337bc9bb07e562a2c4045fec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:02.770779Z","signature_b64":"+Q7xmhk6VA0HloIrWG0bo7eWpI2w08YMoamF8SP6pas8vaXjUVvp4aGgmaNURmvRH6DFf8Y2H+/D2SpLLHYoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b91a92c99bca5b821c5b8de7c1561582cd0c96a893d33ee9020af6473361529","last_reissued_at":"2026-07-05T09:36:02.770388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:02.770388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gregor Kobsik, Isaak Lim, Julius Nehring-Wirxel, Leif Kobbelt, Paula Usinger, Tim Elsner, Victor Czech, Yanjiang He","submitted_at":"2024-11-15T15:36:48Z","abstract_excerpt":"In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the context of images, tokenisation of visual data is usually limited to regular grids obtained from quantisation methods, without global content awareness. Our work improves tokenisation of visual data by bringing Byte Pair Encoding from 1D to multiple dimensions, as a complementary add-on to existing compression. We achieve this through counting constellations of to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10281","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/2411.10281/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":"2411.10281","created_at":"2026-07-05T09:36:02.770449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10281v1","created_at":"2026-07-05T09:36:02.770449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10281","created_at":"2026-07-05T09:36:02.770449+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOI2SLEZXSS3","created_at":"2026-07-05T09:36:02.770449+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOI2SLEZXSS3QIOF","created_at":"2026-07-05T09:36:02.770449+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOI2SLEZ","created_at":"2026-07-05T09:36:02.770449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14411","citing_title":"Byte Pair Encoding for Efficient Time Series Forecasting","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA","json":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA.json","graph_json":"https://pith.science/api/pith-number/HOI2SLEZXSS3QIOFXDPHYFLBLA/graph.json","events_json":"https://pith.science/api/pith-number/HOI2SLEZXSS3QIOFXDPHYFLBLA/events.json","paper":"https://pith.science/paper/HOI2SLEZ"},"agent_actions":{"view_html":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA","download_json":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA.json","view_paper":"https://pith.science/paper/HOI2SLEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10281&json=true","fetch_graph":"https://pith.science/api/pith-number/HOI2SLEZXSS3QIOFXDPHYFLBLA/graph.json","fetch_events":"https://pith.science/api/pith-number/HOI2SLEZXSS3QIOFXDPHYFLBLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA/action/storage_attestation","attest_author":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA/action/author_attestation","sign_citation":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA/action/citation_signature","submit_replication":"https://pith.science/pith/HOI2SLEZXSS3QIOFXDPHYFLBLA/action/replication_record"}},"created_at":"2026-07-05T09:36:02.770449+00:00","updated_at":"2026-07-05T09:36:02.770449+00:00"}