{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SPRQZIL2RBPPIKIAETVMSO5VC3","short_pith_number":"pith:SPRQZIL2","canonical_record":{"source":{"id":"2411.14402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:31:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d770e26372ffb7eb535d9c78aa50b7155ab915f423e3ac9a0434c9afb837825","abstract_canon_sha256":"0cb1e9ee7ab50cfe5a0be3781918d20a8ea790ab2a5692dedc0967d99d5649b6"},"schema_version":"1.0"},"canonical_sha256":"93e30ca17a885ef4290024eac93bb516ceec5fe1e4f926b5386fc838b83c1796","source":{"kind":"arxiv","id":"2411.14402","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14402","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14402v1","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14402","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"SPRQZIL2RBPP","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"SPRQZIL2RBPPIKIA","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"SPRQZIL2","created_at":"2026-07-05T09:38:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SPRQZIL2RBPPIKIAETVMSO5VC3","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:31:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d770e26372ffb7eb535d9c78aa50b7155ab915f423e3ac9a0434c9afb837825","abstract_canon_sha256":"0cb1e9ee7ab50cfe5a0be3781918d20a8ea790ab2a5692dedc0967d99d5649b6"},"schema_version":"1.0"},"canonical_sha256":"93e30ca17a885ef4290024eac93bb516ceec5fe1e4f926b5386fc838b83c1796","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:46.447225Z","signature_b64":"EGwOsVFpN8yneKV8+ayis2QznAg1+ZQs9JrqRA0olUcv7Xi+aNacYqyVTsj3l9X8WPSN7tdONVmxMuvAfnkVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93e30ca17a885ef4290024eac93bb516ceec5fe1e4f926b5386fc838b83c1796","last_reissued_at":"2026-07-05T09:38:46.446706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:46.446706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14402","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":"2026-07-05T09:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ebEbJ0heg1+RT37J8vHD6MBgFka4mR6sUF5x5Kab2HTm+fezt+9eRmOyXPicfZ1s5XNGsMPJWEPEsfvzcP+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:38.635755Z"},"content_sha256":"c98686c9635c6b96ef591efe0ce1d7c7032d550a0157715062ff64bbcfb6406b","schema_version":"1.0","event_id":"sha256:c98686c9635c6b96ef591efe0ce1d7c7032d550a0157715062ff64bbcfb6406b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SPRQZIL2RBPPIKIAETVMSO5VC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alaaeldin El-Nouby, Alexander T Toshev, David Haldimann, Enrico Fini, Joshua M. Susskind, Louis B\\'ethune, Marcin Eichner, Michal Klein, Moin Nabi, Mustafa Shukor, Philipp Dufter, Sai Aitharaju, Victor Guilherme Turrisi da Costa, Xiujun Li, Yinfei Yang, Zhe Gan","submitted_at":"2024-11-21T18:31:25Z","abstract_excerpt":"We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this paper, we present AIMV2, a family of generalist vision encoders characterized by a straightforward pre-training process, scalability, and remarkable performance across a range of downstream tasks. This is achieved by pairing the vision encoder with a multimodal decoder that autoregressively generates raw image patches and text tokens. Our encoders excel not o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14402","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/2411.14402/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":"2026-07-05T09:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDB/9Md9CoKiQRkqgzVrC8rFi949ce/NMWTD9VsC+cBWCpOUdbY6AgMdCfEWnUKbco25xO5MKwcEB2iuwCtPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:38.636140Z"},"content_sha256":"707beb4a354b2fff382dd7620f1704444f7658ae57ca6e58e590d61c5d0f40f7","schema_version":"1.0","event_id":"sha256:707beb4a354b2fff382dd7620f1704444f7658ae57ca6e58e590d61c5d0f40f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/bundle.json","state_url":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/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":"2026-07-09T01:03:38Z","links":{"resolver":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3","bundle":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/bundle.json","state":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SPRQZIL2RBPPIKIAETVMSO5VC3","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":"0cb1e9ee7ab50cfe5a0be3781918d20a8ea790ab2a5692dedc0967d99d5649b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:31:25Z","title_canon_sha256":"3d770e26372ffb7eb535d9c78aa50b7155ab915f423e3ac9a0434c9afb837825"},"schema_version":"1.0","source":{"id":"2411.14402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14402","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14402v1","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14402","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"SPRQZIL2RBPP","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"SPRQZIL2RBPPIKIA","created_at":"2026-07-05T09:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"SPRQZIL2","created_at":"2026-07-05T09:38:46Z"}],"graph_snapshots":[{"event_id":"sha256:707beb4a354b2fff382dd7620f1704444f7658ae57ca6e58e590d61c5d0f40f7","target":"graph","created_at":"2026-07-05T09:38:46Z","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/2411.14402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this paper, we present AIMV2, a family of generalist vision encoders characterized by a straightforward pre-training process, scalability, and remarkable performance across a range of downstream tasks. This is achieved by pairing the vision encoder with a multimodal decoder that autoregressively generates raw image patches and text tokens. Our encoders excel not o","authors_text":"Alaaeldin El-Nouby, Alexander T Toshev, David Haldimann, Enrico Fini, Joshua M. Susskind, Louis B\\'ethune, Marcin Eichner, Michal Klein, Moin Nabi, Mustafa Shukor, Philipp Dufter, Sai Aitharaju, Victor Guilherme Turrisi da Costa, Xiujun Li, Yinfei Yang, Zhe Gan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:31:25Z","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14402","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:c98686c9635c6b96ef591efe0ce1d7c7032d550a0157715062ff64bbcfb6406b","target":"record","created_at":"2026-07-05T09:38:46Z","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":"0cb1e9ee7ab50cfe5a0be3781918d20a8ea790ab2a5692dedc0967d99d5649b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:31:25Z","title_canon_sha256":"3d770e26372ffb7eb535d9c78aa50b7155ab915f423e3ac9a0434c9afb837825"},"schema_version":"1.0","source":{"id":"2411.14402","kind":"arxiv","version":1}},"canonical_sha256":"93e30ca17a885ef4290024eac93bb516ceec5fe1e4f926b5386fc838b83c1796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93e30ca17a885ef4290024eac93bb516ceec5fe1e4f926b5386fc838b83c1796","first_computed_at":"2026-07-05T09:38:46.446706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:46.446706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EGwOsVFpN8yneKV8+ayis2QznAg1+ZQs9JrqRA0olUcv7Xi+aNacYqyVTsj3l9X8WPSN7tdONVmxMuvAfnkVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:46.447225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c98686c9635c6b96ef591efe0ce1d7c7032d550a0157715062ff64bbcfb6406b","sha256:707beb4a354b2fff382dd7620f1704444f7658ae57ca6e58e590d61c5d0f40f7"],"state_sha256":"08ee8d021272a0972a9e73e2bfc0b059f232a60c8bcb9d0a65d0917fc3fa0bd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ehSxwlesGdDSP5EIq2OEHdJ3282dcubYQGaNMyvQDaNo/iFt9fcbW3Qkm8lZe6bxF1CvQ0ZsUxH9FGzlaKwEDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:03:38.638263Z","bundle_sha256":"966710d0e79e10a41f8e01ab367917b94f6f3b8fb4ead2acb2ecfa5099fc4982"}}