{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HQPYPVPZX6HXQPDI57D5PADHD5","short_pith_number":"pith:HQPYPVPZ","canonical_record":{"source":{"id":"2312.00785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"6471d612fe27b08e2fb976e3fabf6670ecc5dbb9c8f38b9b828076273a9b749b","abstract_canon_sha256":"c2bdc823f68d94cbaa0eec770727694aaeb0e117d2b444bf6933be050ca64d84"},"schema_version":"1.0"},"canonical_sha256":"3c1f87d5f9bf8f783c68efc7d780671f446b5b87ef13b4b42423031bcc537c79","source":{"kind":"arxiv","id":"2312.00785","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00785","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00785v1","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00785","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"HQPYPVPZX6HX","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"pith_short_16","alias_value":"HQPYPVPZX6HXQPDI","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"pith_short_8","alias_value":"HQPYPVPZ","created_at":"2026-07-05T07:19:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HQPYPVPZX6HXQPDI57D5PADHD5","target":"record","payload":{"canonical_record":{"source":{"id":"2312.00785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"6471d612fe27b08e2fb976e3fabf6670ecc5dbb9c8f38b9b828076273a9b749b","abstract_canon_sha256":"c2bdc823f68d94cbaa0eec770727694aaeb0e117d2b444bf6933be050ca64d84"},"schema_version":"1.0"},"canonical_sha256":"3c1f87d5f9bf8f783c68efc7d780671f446b5b87ef13b4b42423031bcc537c79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:14.424648Z","signature_b64":"zwNxg8QHEGwrNEtGJYNN/V1fdUcRZYDsdid/JzTe2kwApXcJMiBALYfg5M/lWl3KPuN8luN/rAp0OBsLeyJpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c1f87d5f9bf8f783c68efc7d780671f446b5b87ef13b4b42423031bcc537c79","last_reissued_at":"2026-07-05T07:19:14.424127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:14.424127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.00785","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":"2026-07-05T07:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QXbK5pgAKilwCrvFul89dMl4dnrk2n81ZbxQHDoO2alwJSU78axPrL8fyJ3Q1S4C04/Hkm5jr1IXZkZ852uWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:07:42.710911Z"},"content_sha256":"26a2c199babc23d4c27b81bf4f818b3a4af7038aff2fd380431f6f96ccfcbfac","schema_version":"1.0","event_id":"sha256:26a2c199babc23d4c27b81bf4f818b3a4af7038aff2fd380431f6f96ccfcbfac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HQPYPVPZX6HXQPDI57D5PADHD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Alexei A Efros, Amir Bar, Jitendra Malik, Karttikeya Mangalam, Trevor Darrell, Xinyang Geng, Yutong Bai","submitted_at":"2023-12-01T18:59:57Z","abstract_excerpt":"We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, \"visual sentences\", in which we can represent raw images and videos as well as annotated data sources such as semantic segmentations and depth reconstructions without needing any meta-knowledge beyond the pixels. Once this wide variety of visual data (comprising 420 billion tokens) is represented as sequences, the model can be trained to minimize a cross-entropy loss for next token prediction. By training across va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00785","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/2312.00785/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":"2026-07-05T07:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ViBV5rIKAJncrDTbAR1cpn7dWGu9bouf5f8fYbDKeVfsZ6uPI5STOwQ4AC4TKqocShS314tv0h8V65UlJHgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:07:42.711390Z"},"content_sha256":"c5c9d3acd72654d5b7107ad37a6eafeab530df4c19db07e58d9e82b60bc9f722","schema_version":"1.0","event_id":"sha256:c5c9d3acd72654d5b7107ad37a6eafeab530df4c19db07e58d9e82b60bc9f722"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQPYPVPZX6HXQPDI57D5PADHD5/bundle.json","state_url":"https://pith.science/pith/HQPYPVPZX6HXQPDI57D5PADHD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQPYPVPZX6HXQPDI57D5PADHD5/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":"2026-08-05T05:07:42Z","links":{"resolver":"https://pith.science/pith/HQPYPVPZX6HXQPDI57D5PADHD5","bundle":"https://pith.science/pith/HQPYPVPZX6HXQPDI57D5PADHD5/bundle.json","state":"https://pith.science/pith/HQPYPVPZX6HXQPDI57D5PADHD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQPYPVPZX6HXQPDI57D5PADHD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HQPYPVPZX6HXQPDI57D5PADHD5","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":"c2bdc823f68d94cbaa0eec770727694aaeb0e117d2b444bf6933be050ca64d84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:57Z","title_canon_sha256":"6471d612fe27b08e2fb976e3fabf6670ecc5dbb9c8f38b9b828076273a9b749b"},"schema_version":"1.0","source":{"id":"2312.00785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00785","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00785v1","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00785","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"HQPYPVPZX6HX","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"pith_short_16","alias_value":"HQPYPVPZX6HXQPDI","created_at":"2026-07-05T07:19:14Z"},{"alias_kind":"pith_short_8","alias_value":"HQPYPVPZ","created_at":"2026-07-05T07:19:14Z"}],"graph_snapshots":[{"event_id":"sha256:c5c9d3acd72654d5b7107ad37a6eafeab530df4c19db07e58d9e82b60bc9f722","target":"graph","created_at":"2026-07-05T07:19:14Z","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/2312.00785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, \"visual sentences\", in which we can represent raw images and videos as well as annotated data sources such as semantic segmentations and depth reconstructions without needing any meta-knowledge beyond the pixels. Once this wide variety of visual data (comprising 420 billion tokens) is represented as sequences, the model can be trained to minimize a cross-entropy loss for next token prediction. By training across va","authors_text":"Alan Yuille, Alexei A Efros, Amir Bar, Jitendra Malik, Karttikeya Mangalam, Trevor Darrell, Xinyang Geng, Yutong Bai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:57Z","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00785","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":"sha256:26a2c199babc23d4c27b81bf4f818b3a4af7038aff2fd380431f6f96ccfcbfac","target":"record","created_at":"2026-07-05T07:19:14Z","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":"c2bdc823f68d94cbaa0eec770727694aaeb0e117d2b444bf6933be050ca64d84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:57Z","title_canon_sha256":"6471d612fe27b08e2fb976e3fabf6670ecc5dbb9c8f38b9b828076273a9b749b"},"schema_version":"1.0","source":{"id":"2312.00785","kind":"arxiv","version":1}},"canonical_sha256":"3c1f87d5f9bf8f783c68efc7d780671f446b5b87ef13b4b42423031bcc537c79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c1f87d5f9bf8f783c68efc7d780671f446b5b87ef13b4b42423031bcc537c79","first_computed_at":"2026-07-05T07:19:14.424127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:14.424127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zwNxg8QHEGwrNEtGJYNN/V1fdUcRZYDsdid/JzTe2kwApXcJMiBALYfg5M/lWl3KPuN8luN/rAp0OBsLeyJpCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:14.424648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26a2c199babc23d4c27b81bf4f818b3a4af7038aff2fd380431f6f96ccfcbfac","sha256:c5c9d3acd72654d5b7107ad37a6eafeab530df4c19db07e58d9e82b60bc9f722"],"state_sha256":"895a379d40d0981d48cb1ccef72ca2568ebf5be786df3eb374c18529915f63b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lMyUGY0znULbgIF+gDeheNsw3DljiEr19D2OMfRTIv0KnI5IYlfRpd9UXdRjQaJ7z8kvomeAxuslHh4gb9zqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:07:42.714489Z","bundle_sha256":"e8d161e5a3346f5b58b823b56dc7295716ee3b3d7d9182c8df0c3b4e76127e3e"}}