{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WXLBAWUNDZJPFPCATQP7A2WUZS","short_pith_number":"pith:WXLBAWUN","canonical_record":{"source":{"id":"2310.09199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T15:45:19Z","cross_cats_sorted":[],"title_canon_sha256":"3c3994b04c9c950073f587eb237b7aff67771be96c5c04ae02f9af87e2179245","abstract_canon_sha256":"1ba0c0e43e152e24b94043682d8b83a3f75ddc4deab263372520c3bffa93a45a"},"schema_version":"1.0"},"canonical_sha256":"b5d6105a8d1e52f2bc409c1ff06ad4cc9ce2c03610dbcef9ecfe620ad2a35c90","source":{"kind":"arxiv","id":"2310.09199","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09199","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09199v2","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09199","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_12","alias_value":"WXLBAWUNDZJP","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_16","alias_value":"WXLBAWUNDZJPFPCA","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_8","alias_value":"WXLBAWUN","created_at":"2026-07-05T07:02:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WXLBAWUNDZJPFPCATQP7A2WUZS","target":"record","payload":{"canonical_record":{"source":{"id":"2310.09199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T15:45:19Z","cross_cats_sorted":[],"title_canon_sha256":"3c3994b04c9c950073f587eb237b7aff67771be96c5c04ae02f9af87e2179245","abstract_canon_sha256":"1ba0c0e43e152e24b94043682d8b83a3f75ddc4deab263372520c3bffa93a45a"},"schema_version":"1.0"},"canonical_sha256":"b5d6105a8d1e52f2bc409c1ff06ad4cc9ce2c03610dbcef9ecfe620ad2a35c90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:06.133175Z","signature_b64":"kUk7weQftLHREX0o91zaMYoyhuP91wOwkDKzglz3VB6I1PmnCaxJrjHdk2myToXb13i0lmlkF1lnpXIXPHG4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d6105a8d1e52f2bc409c1ff06ad4cc9ce2c03610dbcef9ecfe620ad2a35c90","last_reissued_at":"2026-07-05T07:02:06.132711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:06.132711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.09199","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":"2026-07-05T07:02:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SmlP8E6sm+NdG+cQ6eWlOiw2hKv77ngx5OaAWbVARTTXvhHAj9w9S3wuGebLALGMSADyWUANTy7YiXAvveAEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:00:34.772925Z"},"content_sha256":"ac7fc597855dbd749ccca40fe4914c558541207cc37922bc5a7a46db01c726fc","schema_version":"1.0","event_id":"sha256:ac7fc597855dbd749ccca40fe4914c558541207cc37922bc5a7a46db01c726fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WXLBAWUNDZJPFPCATQP7A2WUZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Kolesnikov, Basil Mustafa, Daniel Keysers, Daniel Salz, Daniel Vlasic, Filip Pavetic, Ibrahim Alabdulmohsin, Jialin Wu, Keran Rong, Lucas Beyer, Paul Voigtlaender, Piotr Padlewski, Radu Soricut, Sebastian Goodman, Tianli Yu, Xiaohua Zhai, Xiao Wang, Xi Chen, Xi Xiong","submitted_at":"2023-10-13T15:45:19Z","abstract_excerpt":"This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that compares favorably to similar models that are 10x larger. As part of arriving at this strong performance, we compare Vision Transformer (ViT) models pretrained using classification objectives to contrastively (SigLIP) pretrained ones. We find that, while slightly underperforming on standard image classification benchmarks, SigLIP-based PaLI shows superior performance across various multimodal benchmarks, especially on localization and visually-situated text understanding. We scale the SigLIP image enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09199","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/2310.09199/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":"2026-07-05T07:02:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EcLvkNkOQxgbCHj+Sqj73NRwqYMsROQanFnf9mkNQZgney3/9x7WXajTBmwnOZ8C26YwShd6Ne53kprit9hyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:00:34.773423Z"},"content_sha256":"ede96862b0b916855ead18ea5812e4e0623a93ec2834a8fcf1b2cfa37eefbfe3","schema_version":"1.0","event_id":"sha256:ede96862b0b916855ead18ea5812e4e0623a93ec2834a8fcf1b2cfa37eefbfe3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXLBAWUNDZJPFPCATQP7A2WUZS/bundle.json","state_url":"https://pith.science/pith/WXLBAWUNDZJPFPCATQP7A2WUZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXLBAWUNDZJPFPCATQP7A2WUZS/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":"2026-08-04T00:00:34Z","links":{"resolver":"https://pith.science/pith/WXLBAWUNDZJPFPCATQP7A2WUZS","bundle":"https://pith.science/pith/WXLBAWUNDZJPFPCATQP7A2WUZS/bundle.json","state":"https://pith.science/pith/WXLBAWUNDZJPFPCATQP7A2WUZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXLBAWUNDZJPFPCATQP7A2WUZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WXLBAWUNDZJPFPCATQP7A2WUZS","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":"1ba0c0e43e152e24b94043682d8b83a3f75ddc4deab263372520c3bffa93a45a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T15:45:19Z","title_canon_sha256":"3c3994b04c9c950073f587eb237b7aff67771be96c5c04ae02f9af87e2179245"},"schema_version":"1.0","source":{"id":"2310.09199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09199","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09199v2","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09199","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_12","alias_value":"WXLBAWUNDZJP","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_16","alias_value":"WXLBAWUNDZJPFPCA","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_8","alias_value":"WXLBAWUN","created_at":"2026-07-05T07:02:06Z"}],"graph_snapshots":[{"event_id":"sha256:ede96862b0b916855ead18ea5812e4e0623a93ec2834a8fcf1b2cfa37eefbfe3","target":"graph","created_at":"2026-07-05T07:02:06Z","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/2310.09199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that compares favorably to similar models that are 10x larger. As part of arriving at this strong performance, we compare Vision Transformer (ViT) models pretrained using classification objectives to contrastively (SigLIP) pretrained ones. We find that, while slightly underperforming on standard image classification benchmarks, SigLIP-based PaLI shows superior performance across various multimodal benchmarks, especially on localization and visually-situated text understanding. We scale the SigLIP image enco","authors_text":"Alexander Kolesnikov, Basil Mustafa, Daniel Keysers, Daniel Salz, Daniel Vlasic, Filip Pavetic, Ibrahim Alabdulmohsin, Jialin Wu, Keran Rong, Lucas Beyer, Paul Voigtlaender, Piotr Padlewski, Radu Soricut, Sebastian Goodman, Tianli Yu, Xiaohua Zhai, Xiao Wang, Xi Chen, Xi Xiong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T15:45:19Z","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09199","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:ac7fc597855dbd749ccca40fe4914c558541207cc37922bc5a7a46db01c726fc","target":"record","created_at":"2026-07-05T07:02:06Z","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":"1ba0c0e43e152e24b94043682d8b83a3f75ddc4deab263372520c3bffa93a45a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T15:45:19Z","title_canon_sha256":"3c3994b04c9c950073f587eb237b7aff67771be96c5c04ae02f9af87e2179245"},"schema_version":"1.0","source":{"id":"2310.09199","kind":"arxiv","version":2}},"canonical_sha256":"b5d6105a8d1e52f2bc409c1ff06ad4cc9ce2c03610dbcef9ecfe620ad2a35c90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5d6105a8d1e52f2bc409c1ff06ad4cc9ce2c03610dbcef9ecfe620ad2a35c90","first_computed_at":"2026-07-05T07:02:06.132711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:06.132711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kUk7weQftLHREX0o91zaMYoyhuP91wOwkDKzglz3VB6I1PmnCaxJrjHdk2myToXb13i0lmlkF1lnpXIXPHG4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:06.133175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac7fc597855dbd749ccca40fe4914c558541207cc37922bc5a7a46db01c726fc","sha256:ede96862b0b916855ead18ea5812e4e0623a93ec2834a8fcf1b2cfa37eefbfe3"],"state_sha256":"0ff43b28e57fd12808aee42f62f00fccfbe153f2249d79e1bdf26d10f825c0df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUfm046dglhpY3JsDTju0sQhDrg2GB85e1iGpAE+ibgfIDZM4pkToz1fAud9rYMeLkgMJMaq3b3A9kxn9KBWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:00:34.776785Z","bundle_sha256":"8d59af4cc1ddc8d8f1fd8f75f734e65b1b198864ee093157b865b7f04f4d8c88"}}