{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VD4GJCMK2MIPZ6TVHPQBDGUEC3","short_pith_number":"pith:VD4GJCMK","canonical_record":{"source":{"id":"2406.06462","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T16:58:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"51c07b2c6d21fcf49c161eed6f83158f35f31329f3b75e8125ec37673fbad7fd","abstract_canon_sha256":"76a0789529c90a181627eb585d2cf6355b08859204daf2c82394cd0e4d32b981"},"schema_version":"1.0"},"canonical_sha256":"a8f864898ad310fcfa753be0119a8416e4a02d2f8593d15ecd35598a918693c0","source":{"kind":"arxiv","id":"2406.06462","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06462","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06462v4","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06462","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"VD4GJCMK2MIP","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"VD4GJCMK2MIPZ6TV","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"VD4GJCMK","created_at":"2026-07-05T10:50:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VD4GJCMK2MIPZ6TVHPQBDGUEC3","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06462","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T16:58:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"51c07b2c6d21fcf49c161eed6f83158f35f31329f3b75e8125ec37673fbad7fd","abstract_canon_sha256":"76a0789529c90a181627eb585d2cf6355b08859204daf2c82394cd0e4d32b981"},"schema_version":"1.0"},"canonical_sha256":"a8f864898ad310fcfa753be0119a8416e4a02d2f8593d15ecd35598a918693c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:42.431065Z","signature_b64":"1wI6Zm81+B9rLGUi3WbSliLjoZJX5xgA4hwdEWBjJC3Us48EdfZvmxbCgA2nMU8I5ekveAf9EWEd456cDkhyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8f864898ad310fcfa753be0119a8416e4a02d2f8593d15ecd35598a918693c0","last_reissued_at":"2026-07-05T10:50:42.430564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:42.430564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06462","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQlsFz39+kZz3fUxdPARaB6iu+icR5ccjCjmrJRLTSKDn0zhMC9M+5eAnNrZrMdEfKKNBjuH3o+zcqx2RBRFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:35:17.981968Z"},"content_sha256":"c89123cf97adfe6ab5f19b01dc47c37ef96cf5b53d7746608506996406295eb8","schema_version":"1.0","event_id":"sha256:c89123cf97adfe6ab5f19b01dc47c37ef96cf5b53d7746608506996406295eb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VD4GJCMK2MIPZ6TVHPQBDGUEC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bang Liu, Ge Zhang, Jie Fu, Lu Li, Perouz Taslakian, Sai Rajeswar, Suyuchen Wang, Tianyu Zhang, Yoshua Bengio","submitted_at":"2024-06-10T16:58:48Z","abstract_excerpt":"We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06462","kind":"arxiv","version":4},"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/2406.06462/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":"2026-07-05T10:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWanwowx4y1EaaEnytoYF/bgM8mC0EaEPgeOKJtBVaaMcuF3gtwQ43Gse7lUf42jjDjdPuw6nnwoSdAGKEESCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:35:17.982477Z"},"content_sha256":"7a4c930d8e255b16dfa3cc95f02bc7c8ac12bccc371224d51ee64b82f05b31e2","schema_version":"1.0","event_id":"sha256:7a4c930d8e255b16dfa3cc95f02bc7c8ac12bccc371224d51ee64b82f05b31e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VD4GJCMK2MIPZ6TVHPQBDGUEC3/bundle.json","state_url":"https://pith.science/pith/VD4GJCMK2MIPZ6TVHPQBDGUEC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VD4GJCMK2MIPZ6TVHPQBDGUEC3/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":"2026-08-13T05:35:17Z","links":{"resolver":"https://pith.science/pith/VD4GJCMK2MIPZ6TVHPQBDGUEC3","bundle":"https://pith.science/pith/VD4GJCMK2MIPZ6TVHPQBDGUEC3/bundle.json","state":"https://pith.science/pith/VD4GJCMK2MIPZ6TVHPQBDGUEC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VD4GJCMK2MIPZ6TVHPQBDGUEC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VD4GJCMK2MIPZ6TVHPQBDGUEC3","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":"76a0789529c90a181627eb585d2cf6355b08859204daf2c82394cd0e4d32b981","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T16:58:48Z","title_canon_sha256":"51c07b2c6d21fcf49c161eed6f83158f35f31329f3b75e8125ec37673fbad7fd"},"schema_version":"1.0","source":{"id":"2406.06462","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06462","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06462v4","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06462","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"VD4GJCMK2MIP","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"VD4GJCMK2MIPZ6TV","created_at":"2026-07-05T10:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"VD4GJCMK","created_at":"2026-07-05T10:50:42Z"}],"graph_snapshots":[{"event_id":"sha256:7a4c930d8e255b16dfa3cc95f02bc7c8ac12bccc371224d51ee64b82f05b31e2","target":"graph","created_at":"2026-07-05T10:50:42Z","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/2406.06462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked lang","authors_text":"Bang Liu, Ge Zhang, Jie Fu, Lu Li, Perouz Taslakian, Sai Rajeswar, Suyuchen Wang, Tianyu Zhang, Yoshua Bengio","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T16:58:48Z","title":"VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06462","kind":"arxiv","version":4},"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:c89123cf97adfe6ab5f19b01dc47c37ef96cf5b53d7746608506996406295eb8","target":"record","created_at":"2026-07-05T10:50:42Z","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":"76a0789529c90a181627eb585d2cf6355b08859204daf2c82394cd0e4d32b981","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T16:58:48Z","title_canon_sha256":"51c07b2c6d21fcf49c161eed6f83158f35f31329f3b75e8125ec37673fbad7fd"},"schema_version":"1.0","source":{"id":"2406.06462","kind":"arxiv","version":4}},"canonical_sha256":"a8f864898ad310fcfa753be0119a8416e4a02d2f8593d15ecd35598a918693c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8f864898ad310fcfa753be0119a8416e4a02d2f8593d15ecd35598a918693c0","first_computed_at":"2026-07-05T10:50:42.430564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:42.430564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1wI6Zm81+B9rLGUi3WbSliLjoZJX5xgA4hwdEWBjJC3Us48EdfZvmxbCgA2nMU8I5ekveAf9EWEd456cDkhyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:42.431065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06462","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c89123cf97adfe6ab5f19b01dc47c37ef96cf5b53d7746608506996406295eb8","sha256:7a4c930d8e255b16dfa3cc95f02bc7c8ac12bccc371224d51ee64b82f05b31e2"],"state_sha256":"3e38fee1b2d9c0a92db4d56cf9bf93e9a0152c7ec650991b00c87d50d9f1bbd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVRu5K4eivVC4AbUzUE+ANqFTadPuYeTixIPkG3ZRO7CKN0C5jwQXYIC67nfOZVrjNEvy4JYjgs7T9AL6VxOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:35:17.987856Z","bundle_sha256":"7cad43107cb6b8ca79ed43156e0ca8f3cd6aaeac3cfa79ca2247aad17c179b65"}}