{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6RF4HRBD6N5CHGMDKXJORUATOG","short_pith_number":"pith:6RF4HRBD","canonical_record":{"source":{"id":"2312.02147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:59:20Z","cross_cats_sorted":[],"title_canon_sha256":"ff29f03ebbd261ff0388048f4bf4a9f0a24c5f57f3bf7b1eccc7f14426c3f60e","abstract_canon_sha256":"309c06db5864edd864a8511c2c6b5c750f196ed63ce468657b7601579655336f"},"schema_version":"1.0"},"canonical_sha256":"f44bc3c423f37a23998355d2e8d01371a9d5aa224ac4ac708a53fca9d6976fd4","source":{"kind":"arxiv","id":"2312.02147","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02147","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02147v2","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02147","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"6RF4HRBD6N5C","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_16","alias_value":"6RF4HRBD6N5CHGMD","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_8","alias_value":"6RF4HRBD","created_at":"2026-07-05T08:40:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6RF4HRBD6N5CHGMDKXJORUATOG","target":"record","payload":{"canonical_record":{"source":{"id":"2312.02147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:59:20Z","cross_cats_sorted":[],"title_canon_sha256":"ff29f03ebbd261ff0388048f4bf4a9f0a24c5f57f3bf7b1eccc7f14426c3f60e","abstract_canon_sha256":"309c06db5864edd864a8511c2c6b5c750f196ed63ce468657b7601579655336f"},"schema_version":"1.0"},"canonical_sha256":"f44bc3c423f37a23998355d2e8d01371a9d5aa224ac4ac708a53fca9d6976fd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:10.909011Z","signature_b64":"v1A2V9IhV+oKBmn0nsAJjOjXZcyDIup5UNEWo0/+BiqbF2NLljup7zM3sRPeZeszik0hoElVmqLWwfVxS99lAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f44bc3c423f37a23998355d2e8d01371a9d5aa224ac4ac708a53fca9d6976fd4","last_reissued_at":"2026-07-05T08:40:10.908544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:10.908544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.02147","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDzv5XZvKtYDChS6rcbTrZZhT8Xd0OVCUGqqmRlohFyjuyr4T+ckvwtF2ImGjvfq1qyUhsNRccV6WUgGOytzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:39:57.138499Z"},"content_sha256":"1bb8c5c95d2764ab725ceaaf5385da03e2ef5c76947864ad9b8f0e104a7915d6","schema_version":"1.0","event_id":"sha256:1bb8c5c95d2764ab725ceaaf5385da03e2ef5c76947864ad9b8f0e104a7915d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6RF4HRBD6N5CHGMDKXJORUATOG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rejuvenating image-GPT as Strong Visual Representation Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Cihang Xie, Hongru Zhu, Junfei Xiao, Sucheng Ren, Zeyu Wang","submitted_at":"2023-12-04T18:59:20Z","abstract_excerpt":"This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict the next pixels for visual representation learning. Two simple yet essential changes are made. First, we shift the prediction target from raw pixels to semantic tokens, enabling a higher-level understanding of visual content. Second, we supplement the autoregressive modeling by instructing the model to predict not only the next tokens but also the visible tokens. This pipeline is particularly effective when semantic tokens are encoded by discriminatively trained models, such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02147","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/2312.02147/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":"2026-07-05T08:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVfSCQidWki6/AUDYWIDaLPHLkfO0n8Hispv2V9BOzhJpSs0WoPITSgGs6LYkrZbGZ60WmMnMT/W0tGJDo51Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:39:57.138871Z"},"content_sha256":"497dc9b4b09904cab4f125476c4c455a6e37bf57aded8f6c2e13fb7e0e18320e","schema_version":"1.0","event_id":"sha256:497dc9b4b09904cab4f125476c4c455a6e37bf57aded8f6c2e13fb7e0e18320e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RF4HRBD6N5CHGMDKXJORUATOG/bundle.json","state_url":"https://pith.science/pith/6RF4HRBD6N5CHGMDKXJORUATOG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RF4HRBD6N5CHGMDKXJORUATOG/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":"2026-07-12T18:39:57Z","links":{"resolver":"https://pith.science/pith/6RF4HRBD6N5CHGMDKXJORUATOG","bundle":"https://pith.science/pith/6RF4HRBD6N5CHGMDKXJORUATOG/bundle.json","state":"https://pith.science/pith/6RF4HRBD6N5CHGMDKXJORUATOG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RF4HRBD6N5CHGMDKXJORUATOG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6RF4HRBD6N5CHGMDKXJORUATOG","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":"309c06db5864edd864a8511c2c6b5c750f196ed63ce468657b7601579655336f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:59:20Z","title_canon_sha256":"ff29f03ebbd261ff0388048f4bf4a9f0a24c5f57f3bf7b1eccc7f14426c3f60e"},"schema_version":"1.0","source":{"id":"2312.02147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02147","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02147v2","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02147","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"6RF4HRBD6N5C","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_16","alias_value":"6RF4HRBD6N5CHGMD","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_8","alias_value":"6RF4HRBD","created_at":"2026-07-05T08:40:10Z"}],"graph_snapshots":[{"event_id":"sha256:497dc9b4b09904cab4f125476c4c455a6e37bf57aded8f6c2e13fb7e0e18320e","target":"graph","created_at":"2026-07-05T08:40:10Z","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/2312.02147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict the next pixels for visual representation learning. Two simple yet essential changes are made. First, we shift the prediction target from raw pixels to semantic tokens, enabling a higher-level understanding of visual content. Second, we supplement the autoregressive modeling by instructing the model to predict not only the next tokens but also the visible tokens. This pipeline is particularly effective when semantic tokens are encoded by discriminatively trained models, such a","authors_text":"Alan Yuille, Cihang Xie, Hongru Zhu, Junfei Xiao, Sucheng Ren, Zeyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:59:20Z","title":"Rejuvenating image-GPT as Strong Visual Representation Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02147","kind":"arxiv","version":2},"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":"sha256:1bb8c5c95d2764ab725ceaaf5385da03e2ef5c76947864ad9b8f0e104a7915d6","target":"record","created_at":"2026-07-05T08:40:10Z","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":"309c06db5864edd864a8511c2c6b5c750f196ed63ce468657b7601579655336f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:59:20Z","title_canon_sha256":"ff29f03ebbd261ff0388048f4bf4a9f0a24c5f57f3bf7b1eccc7f14426c3f60e"},"schema_version":"1.0","source":{"id":"2312.02147","kind":"arxiv","version":2}},"canonical_sha256":"f44bc3c423f37a23998355d2e8d01371a9d5aa224ac4ac708a53fca9d6976fd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f44bc3c423f37a23998355d2e8d01371a9d5aa224ac4ac708a53fca9d6976fd4","first_computed_at":"2026-07-05T08:40:10.908544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:10.908544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v1A2V9IhV+oKBmn0nsAJjOjXZcyDIup5UNEWo0/+BiqbF2NLljup7zM3sRPeZeszik0hoElVmqLWwfVxS99lAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:10.909011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bb8c5c95d2764ab725ceaaf5385da03e2ef5c76947864ad9b8f0e104a7915d6","sha256:497dc9b4b09904cab4f125476c4c455a6e37bf57aded8f6c2e13fb7e0e18320e"],"state_sha256":"38291ecacab895f40360254f74ee199a250fa74745ead41cf235b06efb2af762"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+m7R3Nossy+VJg31PxhVF4GH+wId7v4vJPKrlb9+e/QdybEqkLiCuVvlOtpAEtYn+OK0KeKrrydibzV6zQhwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T18:39:57.140953Z","bundle_sha256":"e32356e6a749d871e0cae3e992de65d0f59f2d96c5cb2fe04dd14b616710b730"}}