{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DVEXLPK72FACRCXNWACFWNUW2I","short_pith_number":"pith:DVEXLPK7","schema_version":"1.0","canonical_sha256":"1d4975bd5fd140288aedb0045b3696d238f0d7d8b9ee85845148cacaa2fd3f42","source":{"kind":"arxiv","id":"2312.10457","version":1},"attestation_state":"computed","paper":{"title":"Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyou Song, Shan Zhang, Tong Wang","submitted_at":"2023-12-16T14:03:10Z","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"},"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":"2312.10457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T14:03:10Z","cross_cats_sorted":[],"title_canon_sha256":"25d800c611053dd1c0f48b4dc532eacc5fbfd6d2f0c3a7ff0983ad4d1dfaeddb","abstract_canon_sha256":"0371f509a1ffc6cecda74996195576167837e326ee0ee43cc61575bd58219ed9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:06.889777Z","signature_b64":"3PPgLBX5uInZbsLHipM1KTrMBqLmjTxQcL/kWKu33i8rdFY8nxYNd9Bfn7BwgcZd3kCGMe+v+hX8In8mBQ8QAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d4975bd5fd140288aedb0045b3696d238f0d7d8b9ee85845148cacaa2fd3f42","last_reissued_at":"2026-07-05T07:25:06.889329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:06.889329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyou Song, Shan Zhang, Tong Wang","submitted_at":"2023-12-16T14:03:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10457","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/2312.10457/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":"2312.10457","created_at":"2026-07-05T07:25:06.889394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10457v1","created_at":"2026-07-05T07:25:06.889394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10457","created_at":"2026-07-05T07:25:06.889394+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVEXLPK72FAC","created_at":"2026-07-05T07:25:06.889394+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVEXLPK72FACRCXN","created_at":"2026-07-05T07:25:06.889394+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVEXLPK7","created_at":"2026-07-05T07:25:06.889394+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/DVEXLPK72FACRCXNWACFWNUW2I","json":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I.json","graph_json":"https://pith.science/api/pith-number/DVEXLPK72FACRCXNWACFWNUW2I/graph.json","events_json":"https://pith.science/api/pith-number/DVEXLPK72FACRCXNWACFWNUW2I/events.json","paper":"https://pith.science/paper/DVEXLPK7"},"agent_actions":{"view_html":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I","download_json":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I.json","view_paper":"https://pith.science/paper/DVEXLPK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10457&json=true","fetch_graph":"https://pith.science/api/pith-number/DVEXLPK72FACRCXNWACFWNUW2I/graph.json","fetch_events":"https://pith.science/api/pith-number/DVEXLPK72FACRCXNWACFWNUW2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/action/storage_attestation","attest_author":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/action/author_attestation","sign_citation":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/action/citation_signature","submit_replication":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/action/replication_record"}},"created_at":"2026-07-05T07:25:06.889394+00:00","updated_at":"2026-07-05T07:25:06.889394+00:00"}