{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DVEXLPK72FACRCXNWACFWNUW2I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0371f509a1ffc6cecda74996195576167837e326ee0ee43cc61575bd58219ed9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T14:03:10Z","title_canon_sha256":"25d800c611053dd1c0f48b4dc532eacc5fbfd6d2f0c3a7ff0983ad4d1dfaeddb"},"schema_version":"1.0","source":{"id":"2312.10457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10457","created_at":"2026-07-05T07:25:06Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10457v1","created_at":"2026-07-05T07:25:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10457","created_at":"2026-07-05T07:25:06Z"},{"alias_kind":"pith_short_12","alias_value":"DVEXLPK72FAC","created_at":"2026-07-05T07:25:06Z"},{"alias_kind":"pith_short_16","alias_value":"DVEXLPK72FACRCXN","created_at":"2026-07-05T07:25:06Z"},{"alias_kind":"pith_short_8","alias_value":"DVEXLPK7","created_at":"2026-07-05T07:25:06Z"}],"graph_snapshots":[{"event_id":"sha256:9378ca451955c9bd3e0000d32cde28b07a8cccf971571f8500ade53c1faf9c1a","target":"graph","created_at":"2026-07-05T07:25:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.10457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of autoregressive modeling (AM) in computer vision lags behind natural language processing (NLP) in self-supervised pre-training. This is mainly caused by the challenge that images are not sequential signals and lack a natural order when applying autoregressive modeling. In this study, inspired by human beings' way of grasping an image, i.e., focusing on the main object first, we present a semantic-aware autoregressive image modeling (SemAIM) method to tackle this challenge. The key insight of SemAIM is to autoregressive model images from the semantic patches to the less semant","authors_text":"Kaiyou Song, Shan Zhang, Tong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T14:03:10Z","title":"Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10457","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:28c32e7891b72506b06bd0bb6e1dd8fe6bdebc5510e46c949db72fae93f4e350","target":"record","created_at":"2026-07-05T07:25:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0371f509a1ffc6cecda74996195576167837e326ee0ee43cc61575bd58219ed9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T14:03:10Z","title_canon_sha256":"25d800c611053dd1c0f48b4dc532eacc5fbfd6d2f0c3a7ff0983ad4d1dfaeddb"},"schema_version":"1.0","source":{"id":"2312.10457","kind":"arxiv","version":1}},"canonical_sha256":"1d4975bd5fd140288aedb0045b3696d238f0d7d8b9ee85845148cacaa2fd3f42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d4975bd5fd140288aedb0045b3696d238f0d7d8b9ee85845148cacaa2fd3f42","first_computed_at":"2026-07-05T07:25:06.889329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:06.889329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3PPgLBX5uInZbsLHipM1KTrMBqLmjTxQcL/kWKu33i8rdFY8nxYNd9Bfn7BwgcZd3kCGMe+v+hX8In8mBQ8QAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:06.889777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28c32e7891b72506b06bd0bb6e1dd8fe6bdebc5510e46c949db72fae93f4e350","sha256:9378ca451955c9bd3e0000d32cde28b07a8cccf971571f8500ade53c1faf9c1a"],"state_sha256":"ce97f188eb317052aec2e3ab83882089ad82bbdb26b93c573cd98ca40d8eb1ff"}