{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:26PU5CCTKYLCDXMEX7JYHCUPMV","short_pith_number":"pith:26PU5CCT","schema_version":"1.0","canonical_sha256":"d79f4e8853561621dd84bfd3838a8f65650190094687f8d81624158ab5cf424d","source":{"kind":"arxiv","id":"2411.15648","version":2},"attestation_state":"computed","paper":{"title":"Sample- and Parameter-Efficient Auto-Regressive Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Bronstein, Elad Amrani, Leonid Karlinsky","submitted_at":"2024-11-23T20:40:46Z","abstract_excerpt":"We introduce XTRA, a vision model pre-trained with a novel auto-regressive objective that significantly enhances both sample and parameter efficiency compared to previous auto-regressive image models. Unlike contrastive or masked image modeling methods, which have not been demonstrated as having consistent scaling behavior on unbalanced internet data, auto-regressive vision models exhibit scalable and promising performance as model and dataset size increase. In contrast to standard auto-regressive models, XTRA employs a Block Causal Mask, where each Block represents k $\\times$ k tokens rather "},"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":"2411.15648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T20:40:46Z","cross_cats_sorted":[],"title_canon_sha256":"4a5e6b1ac0adf7a10a11d6dd416aa2d5463fbde6a168b3e34419fa0f09aca64c","abstract_canon_sha256":"ce4fa5fd370c824682647eedf4d737f572adaeae183d7e378dc8d8848c9c320f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:06.545278Z","signature_b64":"bvCz7+5ZKIrxQjhMisKawF5UsAhyZTttwZzTIxSIGdzvdOVOOtR0fWzB0uO8O+j+nWSacROduPCLai6mvI9iCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79f4e8853561621dd84bfd3838a8f65650190094687f8d81624158ab5cf424d","last_reissued_at":"2026-07-05T10:37:06.544697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:06.544697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample- and Parameter-Efficient Auto-Regressive Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Bronstein, Elad Amrani, Leonid Karlinsky","submitted_at":"2024-11-23T20:40:46Z","abstract_excerpt":"We introduce XTRA, a vision model pre-trained with a novel auto-regressive objective that significantly enhances both sample and parameter efficiency compared to previous auto-regressive image models. Unlike contrastive or masked image modeling methods, which have not been demonstrated as having consistent scaling behavior on unbalanced internet data, auto-regressive vision models exhibit scalable and promising performance as model and dataset size increase. In contrast to standard auto-regressive models, XTRA employs a Block Causal Mask, where each Block represents k $\\times$ k tokens rather "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15648","kind":"arxiv","version":2},"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/2411.15648/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":"2411.15648","created_at":"2026-07-05T10:37:06.544750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15648v2","created_at":"2026-07-05T10:37:06.544750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15648","created_at":"2026-07-05T10:37:06.544750+00:00"},{"alias_kind":"pith_short_12","alias_value":"26PU5CCTKYLC","created_at":"2026-07-05T10:37:06.544750+00:00"},{"alias_kind":"pith_short_16","alias_value":"26PU5CCTKYLCDXME","created_at":"2026-07-05T10:37:06.544750+00:00"},{"alias_kind":"pith_short_8","alias_value":"26PU5CCT","created_at":"2026-07-05T10:37:06.544750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25012","citing_title":"Learning from Semantic Dictionaries: Discriminative Codebook Contrastive Learning for Unified Visual Representation and Generation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV","json":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV.json","graph_json":"https://pith.science/api/pith-number/26PU5CCTKYLCDXMEX7JYHCUPMV/graph.json","events_json":"https://pith.science/api/pith-number/26PU5CCTKYLCDXMEX7JYHCUPMV/events.json","paper":"https://pith.science/paper/26PU5CCT"},"agent_actions":{"view_html":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV","download_json":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV.json","view_paper":"https://pith.science/paper/26PU5CCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15648&json=true","fetch_graph":"https://pith.science/api/pith-number/26PU5CCTKYLCDXMEX7JYHCUPMV/graph.json","fetch_events":"https://pith.science/api/pith-number/26PU5CCTKYLCDXMEX7JYHCUPMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV/action/storage_attestation","attest_author":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV/action/author_attestation","sign_citation":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV/action/citation_signature","submit_replication":"https://pith.science/pith/26PU5CCTKYLCDXMEX7JYHCUPMV/action/replication_record"}},"created_at":"2026-07-05T10:37:06.544750+00:00","updated_at":"2026-07-05T10:37:06.544750+00:00"}