{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EMPA7IHF5NGQPSUA6CP3IOL46B","short_pith_number":"pith:EMPA7IHF","canonical_record":{"source":{"id":"2403.03346","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T22:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"815ca53e9105b88b6f94240ebdccd8f5cea6a17541d721c0ae136b088c857c44","abstract_canon_sha256":"45875c4f3dc1cc6a635ac0ca2c8c3734b47d4c8c370d7fb4fbd08571fde97e17"},"schema_version":"1.0"},"canonical_sha256":"231e0fa0e5eb4d07ca80f09fb4397cf075eea54109bb5267b03730c3098b2e2f","source":{"kind":"arxiv","id":"2403.03346","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03346","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03346v2","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03346","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"pith_short_12","alias_value":"EMPA7IHF5NGQ","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"EMPA7IHF5NGQPSUA","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"EMPA7IHF","created_at":"2026-07-05T10:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EMPA7IHF5NGQPSUA6CP3IOL46B","target":"record","payload":{"canonical_record":{"source":{"id":"2403.03346","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T22:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"815ca53e9105b88b6f94240ebdccd8f5cea6a17541d721c0ae136b088c857c44","abstract_canon_sha256":"45875c4f3dc1cc6a635ac0ca2c8c3734b47d4c8c370d7fb4fbd08571fde97e17"},"schema_version":"1.0"},"canonical_sha256":"231e0fa0e5eb4d07ca80f09fb4397cf075eea54109bb5267b03730c3098b2e2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:19.847212Z","signature_b64":"upMIoK3uV34jdU3v6byoMNI4wDs4H0K1jyT3yGWYmMAJMqfDPNV0HLkG3LW1DgSchKNcp5GDJ4vQeV8NCXrMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"231e0fa0e5eb4d07ca80f09fb4397cf075eea54109bb5267b03730c3098b2e2f","last_reissued_at":"2026-07-05T10:30:19.846670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:19.846670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.03346","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":"2026-07-05T10:30:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1v8XHONijMgTC+8uRA2B9fojVdH3vxe9ALefiwdlTa6CNA0ebvnKS0pQqPm360d2aFBFgT/ZnRggY9VXYsOZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:28:31.456871Z"},"content_sha256":"2d32ee48fa936ffc9994655a64c4c1297d0979a7b1a59fec120d4327dc543924","schema_version":"1.0","event_id":"sha256:2d32ee48fa936ffc9994655a64c4c1297d0979a7b1a59fec120d4327dc543924"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EMPA7IHF5NGQPSUA6CP3IOL46B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Vision-Language Pre-training with Rich Supervisions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edouard Belval, Kunyu Shi, Oren Nuriel, Pengkai Zhu, Shabnam Ghadar, Srikar Appalaraju, Stefano Soatto, Vijay Mahadevan, Yuan Gao, Zhuowen Tu","submitted_at":"2024-03-05T22:14:58Z","abstract_excerpt":"We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. Using web screenshots unlocks a treasure trove of visual and textual cues that are not present in using image-text pairs. In S4, we leverage the inherent tree-structured hierarchy of HTML elements and the spatial localization to carefully design 10 pre-training tasks with large scale annotated data. These tasks resemble downstream tasks across different domains and the annotations are cheap to obtain. We demonstrate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03346","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/2403.03346/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":"2026-07-05T10:30:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5TPhs3OJexcLdCIIQjotDiGA46RcC78uM9S2vntL/INiB1t8tHPh/Y8ZbM2oNZy8cZ9hxy9+DcX3OfEVc2UnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:28:31.457999Z"},"content_sha256":"0a2d5a1cb49f5122afc8d3b2bace3a514e85eb6b8f41d07b43548eb680af6d50","schema_version":"1.0","event_id":"sha256:0a2d5a1cb49f5122afc8d3b2bace3a514e85eb6b8f41d07b43548eb680af6d50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMPA7IHF5NGQPSUA6CP3IOL46B/bundle.json","state_url":"https://pith.science/pith/EMPA7IHF5NGQPSUA6CP3IOL46B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMPA7IHF5NGQPSUA6CP3IOL46B/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":"2026-08-11T21:28:31Z","links":{"resolver":"https://pith.science/pith/EMPA7IHF5NGQPSUA6CP3IOL46B","bundle":"https://pith.science/pith/EMPA7IHF5NGQPSUA6CP3IOL46B/bundle.json","state":"https://pith.science/pith/EMPA7IHF5NGQPSUA6CP3IOL46B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMPA7IHF5NGQPSUA6CP3IOL46B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EMPA7IHF5NGQPSUA6CP3IOL46B","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":"45875c4f3dc1cc6a635ac0ca2c8c3734b47d4c8c370d7fb4fbd08571fde97e17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T22:14:58Z","title_canon_sha256":"815ca53e9105b88b6f94240ebdccd8f5cea6a17541d721c0ae136b088c857c44"},"schema_version":"1.0","source":{"id":"2403.03346","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03346","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03346v2","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03346","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"pith_short_12","alias_value":"EMPA7IHF5NGQ","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"EMPA7IHF5NGQPSUA","created_at":"2026-07-05T10:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"EMPA7IHF","created_at":"2026-07-05T10:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:0a2d5a1cb49f5122afc8d3b2bace3a514e85eb6b8f41d07b43548eb680af6d50","target":"graph","created_at":"2026-07-05T10:30:19Z","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/2403.03346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. Using web screenshots unlocks a treasure trove of visual and textual cues that are not present in using image-text pairs. In S4, we leverage the inherent tree-structured hierarchy of HTML elements and the spatial localization to carefully design 10 pre-training tasks with large scale annotated data. These tasks resemble downstream tasks across different domains and the annotations are cheap to obtain. We demonstrate t","authors_text":"Edouard Belval, Kunyu Shi, Oren Nuriel, Pengkai Zhu, Shabnam Ghadar, Srikar Appalaraju, Stefano Soatto, Vijay Mahadevan, Yuan Gao, Zhuowen Tu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T22:14:58Z","title":"Enhancing Vision-Language Pre-training with Rich Supervisions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03346","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":"sha256:2d32ee48fa936ffc9994655a64c4c1297d0979a7b1a59fec120d4327dc543924","target":"record","created_at":"2026-07-05T10:30:19Z","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":"45875c4f3dc1cc6a635ac0ca2c8c3734b47d4c8c370d7fb4fbd08571fde97e17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T22:14:58Z","title_canon_sha256":"815ca53e9105b88b6f94240ebdccd8f5cea6a17541d721c0ae136b088c857c44"},"schema_version":"1.0","source":{"id":"2403.03346","kind":"arxiv","version":2}},"canonical_sha256":"231e0fa0e5eb4d07ca80f09fb4397cf075eea54109bb5267b03730c3098b2e2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"231e0fa0e5eb4d07ca80f09fb4397cf075eea54109bb5267b03730c3098b2e2f","first_computed_at":"2026-07-05T10:30:19.846670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:19.846670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"upMIoK3uV34jdU3v6byoMNI4wDs4H0K1jyT3yGWYmMAJMqfDPNV0HLkG3LW1DgSchKNcp5GDJ4vQeV8NCXrMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:19.847212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03346","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d32ee48fa936ffc9994655a64c4c1297d0979a7b1a59fec120d4327dc543924","sha256:0a2d5a1cb49f5122afc8d3b2bace3a514e85eb6b8f41d07b43548eb680af6d50"],"state_sha256":"338d77cbdcf5d6c07778424fae2b0beddf8e36f33961ffc2f6299445395ec3b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPKuK+djhWDKHJ0V2M/Rnay0eKEEVtZFe083OQsRsbAh7xVx5oSVlOMltIdiPsPCuHdyKI86fU3uI5ya0s2mCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:28:31.465867Z","bundle_sha256":"dfc6a70ace8b00f7012ca1511778563d1693aab9b03fc9773973f37d5fc68817"}}