{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BL5VTNRRCQK2SSJSE6UDG35HQJ","short_pith_number":"pith:BL5VTNRR","schema_version":"1.0","canonical_sha256":"0afb59b6311415a9493227a8336fa782720100e114cd8b47d6d63cf7705e2b97","source":{"kind":"arxiv","id":"2311.00522","version":1},"attestation_state":"computed","paper":{"title":"Text Rendering Strategies for Pixel Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Elizabeth Salesky, Jonas F. Lotz, Phillip Rust","submitted_at":"2023-11-01T13:49:31Z","abstract_excerpt":"Pixel-based language models process text rendered as images, which allows them to handle any script, making them a promising approach to open vocabulary language modelling. However, recent approaches use text renderers that produce a large set of almost-equivalent input patches, which may prove sub-optimal for downstream tasks, due to redundancy in the input representations. In this paper, we investigate four approaches to rendering text in the PIXEL model (Rust et al., 2023), and find that simple character bigram rendering brings improved performance on sentence-level tasks without compromisi"},"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":"2311.00522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T13:49:31Z","cross_cats_sorted":[],"title_canon_sha256":"4c93024a3fc08bf33ab37987e9098dce9486a113d9491ab977ed1ace8924213a","abstract_canon_sha256":"bfbdcd8096e674320186d03a84e068d97bc065951280dcd00c369a6f77fb7372"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:58.979643Z","signature_b64":"x7mbq8oSkRISUib/FZtbGD7l7GjIxpGN/kmYGrM7cKUt7WwmKO/gaswK6Z9S3nf+3MFRg4TQVqr+aUSlvgaICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0afb59b6311415a9493227a8336fa782720100e114cd8b47d6d63cf7705e2b97","last_reissued_at":"2026-07-05T07:07:58.979234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:58.979234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Rendering Strategies for Pixel Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Elizabeth Salesky, Jonas F. Lotz, Phillip Rust","submitted_at":"2023-11-01T13:49:31Z","abstract_excerpt":"Pixel-based language models process text rendered as images, which allows them to handle any script, making them a promising approach to open vocabulary language modelling. However, recent approaches use text renderers that produce a large set of almost-equivalent input patches, which may prove sub-optimal for downstream tasks, due to redundancy in the input representations. In this paper, we investigate four approaches to rendering text in the PIXEL model (Rust et al., 2023), and find that simple character bigram rendering brings improved performance on sentence-level tasks without compromisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00522","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/2311.00522/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":"2311.00522","created_at":"2026-07-05T07:07:58.979287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00522v1","created_at":"2026-07-05T07:07:58.979287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00522","created_at":"2026-07-05T07:07:58.979287+00:00"},{"alias_kind":"pith_short_12","alias_value":"BL5VTNRRCQK2","created_at":"2026-07-05T07:07:58.979287+00:00"},{"alias_kind":"pith_short_16","alias_value":"BL5VTNRRCQK2SSJS","created_at":"2026-07-05T07:07:58.979287+00:00"},{"alias_kind":"pith_short_8","alias_value":"BL5VTNRR","created_at":"2026-07-05T07:07:58.979287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ","json":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ.json","graph_json":"https://pith.science/api/pith-number/BL5VTNRRCQK2SSJSE6UDG35HQJ/graph.json","events_json":"https://pith.science/api/pith-number/BL5VTNRRCQK2SSJSE6UDG35HQJ/events.json","paper":"https://pith.science/paper/BL5VTNRR"},"agent_actions":{"view_html":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ","download_json":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ.json","view_paper":"https://pith.science/paper/BL5VTNRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00522&json=true","fetch_graph":"https://pith.science/api/pith-number/BL5VTNRRCQK2SSJSE6UDG35HQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BL5VTNRRCQK2SSJSE6UDG35HQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ/action/storage_attestation","attest_author":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ/action/author_attestation","sign_citation":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ/action/citation_signature","submit_replication":"https://pith.science/pith/BL5VTNRRCQK2SSJSE6UDG35HQJ/action/replication_record"}},"created_at":"2026-07-05T07:07:58.979287+00:00","updated_at":"2026-07-05T07:07:58.979287+00:00"}