{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YDFX6UKCTTDQZGVTOPCZF5IWPI","short_pith_number":"pith:YDFX6UKC","schema_version":"1.0","canonical_sha256":"c0cb7f51429cc70c9ab373c592f5167a3e2b0b51147c282797aff2aaeec91c5d","source":{"kind":"arxiv","id":"2507.07995","version":1},"attestation_state":"computed","paper":{"title":"Single-pass Adaptive Image Tokenization for Minimum Program Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Phillip Isola, Sanghyun Byun, Shivam Duggal, William T. Freeman","submitted_at":"2025-07-10T17:59:53Z","abstract_excerpt":"According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low Kolmogorov Complexity (KC). In contrast, most visual representation learning systems use fixed-length representations for all inputs, ignoring variations in complexity or familiarity. Recent adaptive tokenization methods address this by allocating variable-length representations but typically require test-time search over multiple encodings to find the most predictive one. Inspired by Kolmogorov Complexity principles,"},"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":"2507.07995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T17:59:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"813a10caf9cbcd356550b52534562216cc06b6f3d6e67d5963fe85bd7e9b7379","abstract_canon_sha256":"2ef3ce3ab100e5d906e91bd3d35f4e78bb61f7bf1ad04f16500954cf2c23e202"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:08.345435Z","signature_b64":"KrJQpYCpSanyGw7VzYXMupC36DcWVA/R3tph4UzokxDZ7m24lrwC0F0EMx4fP/PT1o5iOK0n+oW4GAv0CB2zCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0cb7f51429cc70c9ab373c592f5167a3e2b0b51147c282797aff2aaeec91c5d","last_reissued_at":"2026-07-05T11:35:08.344853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:08.344853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-pass Adaptive Image Tokenization for Minimum Program Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Phillip Isola, Sanghyun Byun, Shivam Duggal, William T. Freeman","submitted_at":"2025-07-10T17:59:53Z","abstract_excerpt":"According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low Kolmogorov Complexity (KC). In contrast, most visual representation learning systems use fixed-length representations for all inputs, ignoring variations in complexity or familiarity. Recent adaptive tokenization methods address this by allocating variable-length representations but typically require test-time search over multiple encodings to find the most predictive one. Inspired by Kolmogorov Complexity principles,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07995","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/2507.07995/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":"2507.07995","created_at":"2026-07-05T11:35:08.344914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07995v1","created_at":"2026-07-05T11:35:08.344914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07995","created_at":"2026-07-05T11:35:08.344914+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDFX6UKCTTDQ","created_at":"2026-07-05T11:35:08.344914+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDFX6UKCTTDQZGVT","created_at":"2026-07-05T11:35:08.344914+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDFX6UKC","created_at":"2026-07-05T11:35:08.344914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06158","citing_title":"Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04461","citing_title":"ChannelTok: Efficient Flexible-Length Vision Tokenization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI","json":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI.json","graph_json":"https://pith.science/api/pith-number/YDFX6UKCTTDQZGVTOPCZF5IWPI/graph.json","events_json":"https://pith.science/api/pith-number/YDFX6UKCTTDQZGVTOPCZF5IWPI/events.json","paper":"https://pith.science/paper/YDFX6UKC"},"agent_actions":{"view_html":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI","download_json":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI.json","view_paper":"https://pith.science/paper/YDFX6UKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07995&json=true","fetch_graph":"https://pith.science/api/pith-number/YDFX6UKCTTDQZGVTOPCZF5IWPI/graph.json","fetch_events":"https://pith.science/api/pith-number/YDFX6UKCTTDQZGVTOPCZF5IWPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI/action/storage_attestation","attest_author":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI/action/author_attestation","sign_citation":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI/action/citation_signature","submit_replication":"https://pith.science/pith/YDFX6UKCTTDQZGVTOPCZF5IWPI/action/replication_record"}},"created_at":"2026-07-05T11:35:08.344914+00:00","updated_at":"2026-07-05T11:35:08.344914+00:00"}