{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KXAIZOKQOMUWCV4GWEA5D5USB5","short_pith_number":"pith:KXAIZOKQ","schema_version":"1.0","canonical_sha256":"55c08cb9507329615786b101d1f6920f41efdea3e09f495d7b151f96dde4a284","source":{"kind":"arxiv","id":"2605.27696","version":1},"attestation_state":"computed","paper":{"title":"Structure over Pixels: Learning Variable-Length Visual Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kacper Dobek, Krzysztof Krawiec, Piotr Wyrwi\\'nski","submitted_at":"2026-05-26T21:16:04Z","abstract_excerpt":"Discrete visual tokenizers translate images into ordered sequences of codes, providing a natural representation for structural description of scenes. Yet existing adaptive tokenizers either require post-hoc search or select among a discrete set of pre-trained rates, rather than learning a continuous per-image sequence length coupled to the model and scene, and they typically train against pixel reconstruction, emphasizing texture rather than structure. We propose STROP, a discrete visual tokenizer architecture that forms structural scene representations and simultaneously learns how long an im"},"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":"2605.27696","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T21:16:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1707c6d57c87eb86a5a9a512b744196e2a192284f7ac3c9e907a8e5e1f64fb1","abstract_canon_sha256":"ea30a9e5e4f2fae1c0d6525f3beb55af2fc82776bf1acd603ce996eccafb42d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:46.470690Z","signature_b64":"MYgqXMpJzUiXtL2ndzaNGi5dzdxB0QRbGJ/h3woB4FTaRpLlZNrBdGiRG6yeM2Y4mOYa0UTIa3dzskyBg5CYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55c08cb9507329615786b101d1f6920f41efdea3e09f495d7b151f96dde4a284","last_reissued_at":"2026-05-28T01:04:46.470302Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:46.470302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure over Pixels: Learning Variable-Length Visual Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kacper Dobek, Krzysztof Krawiec, Piotr Wyrwi\\'nski","submitted_at":"2026-05-26T21:16:04Z","abstract_excerpt":"Discrete visual tokenizers translate images into ordered sequences of codes, providing a natural representation for structural description of scenes. Yet existing adaptive tokenizers either require post-hoc search or select among a discrete set of pre-trained rates, rather than learning a continuous per-image sequence length coupled to the model and scene, and they typically train against pixel reconstruction, emphasizing texture rather than structure. We propose STROP, a discrete visual tokenizer architecture that forms structural scene representations and simultaneously learns how long an im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27696","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/2605.27696/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":"2605.27696","created_at":"2026-05-28T01:04:46.470368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27696v1","created_at":"2026-05-28T01:04:46.470368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27696","created_at":"2026-05-28T01:04:46.470368+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXAIZOKQOMUW","created_at":"2026-05-28T01:04:46.470368+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXAIZOKQOMUWCV4G","created_at":"2026-05-28T01:04:46.470368+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXAIZOKQ","created_at":"2026-05-28T01:04:46.470368+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/KXAIZOKQOMUWCV4GWEA5D5USB5","json":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5.json","graph_json":"https://pith.science/api/pith-number/KXAIZOKQOMUWCV4GWEA5D5USB5/graph.json","events_json":"https://pith.science/api/pith-number/KXAIZOKQOMUWCV4GWEA5D5USB5/events.json","paper":"https://pith.science/paper/KXAIZOKQ"},"agent_actions":{"view_html":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5","download_json":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5.json","view_paper":"https://pith.science/paper/KXAIZOKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27696&json=true","fetch_graph":"https://pith.science/api/pith-number/KXAIZOKQOMUWCV4GWEA5D5USB5/graph.json","fetch_events":"https://pith.science/api/pith-number/KXAIZOKQOMUWCV4GWEA5D5USB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5/action/storage_attestation","attest_author":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5/action/author_attestation","sign_citation":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5/action/citation_signature","submit_replication":"https://pith.science/pith/KXAIZOKQOMUWCV4GWEA5D5USB5/action/replication_record"}},"created_at":"2026-05-28T01:04:46.470368+00:00","updated_at":"2026-05-28T01:04:46.470368+00:00"}