{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DVEXLPK72FACRCXNWACFWNUW2I","short_pith_number":"pith:DVEXLPK7","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"},"canonical_sha256":"1d4975bd5fd140288aedb0045b3696d238f0d7d8b9ee85845148cacaa2fd3f42","source":{"kind":"arxiv","id":"2312.10457","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DVEXLPK72FACRCXNWACFWNUW2I","target":"record","payload":{"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"},"canonical_sha256":"1d4975bd5fd140288aedb0045b3696d238f0d7d8b9ee85845148cacaa2fd3f42","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"},"source_kind":"arxiv","source_id":"2312.10457","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxJej9x7oRgs/w8tFjyXAN30F67QbGhP070JReM/sLawCGfj5Vj+PE7NEEDPTXAhbbs4hJIl9VWKSUa2kjHZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:19:09.801656Z"},"content_sha256":"28c32e7891b72506b06bd0bb6e1dd8fe6bdebc5510e46c949db72fae93f4e350","schema_version":"1.0","event_id":"sha256:28c32e7891b72506b06bd0bb6e1dd8fe6bdebc5510e46c949db72fae93f4e350"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DVEXLPK72FACRCXNWACFWNUW2I","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GnAOQ9fXj44YyNjB05wN7n064GZFpZTBZpgo16PkneknT0tGzO/+Rc8OnigF5dDukTdJebfof4qLE2ICgwiuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:19:09.802607Z"},"content_sha256":"9378ca451955c9bd3e0000d32cde28b07a8cccf971571f8500ade53c1faf9c1a","schema_version":"1.0","event_id":"sha256:9378ca451955c9bd3e0000d32cde28b07a8cccf971571f8500ade53c1faf9c1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/bundle.json","state_url":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVEXLPK72FACRCXNWACFWNUW2I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T01:19:09Z","links":{"resolver":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I","bundle":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/bundle.json","state":"https://pith.science/pith/DVEXLPK72FACRCXNWACFWNUW2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVEXLPK72FACRCXNWACFWNUW2I/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y01WAELirjfu/FHRoLnDTkHjB0wckqLhFngnbIzCWJTCJz2YWWe9yqApDND4+6GJEMcyIxc5l3OUIF9SkuCoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:19:09.809884Z","bundle_sha256":"25d11b12df59a497907bccba9929ab2f70072b50fde0b060e42f900db4286cc8"}}