{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SNVMO3T4AIDJF77LGVH5YC2PMT","short_pith_number":"pith:SNVMO3T4","canonical_record":{"source":{"id":"2309.16511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-28T15:18:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"cc977a35a293fe022e077f3e6bf1281e8d6093ae7dd0a5670ae3cdbd40904c46","abstract_canon_sha256":"8c618ee8b31c2adea1cb809922cd06e751daa79a71229e33e3f7266be1849ba1"},"schema_version":"1.0"},"canonical_sha256":"936ac76e7c020692ffeb354fdc0b4f64fe4dce12a1e3bdaabd23ba9dd9f70a91","source":{"kind":"arxiv","id":"2309.16511","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16511","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16511v1","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16511","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"pith_short_12","alias_value":"SNVMO3T4AIDJ","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"pith_short_16","alias_value":"SNVMO3T4AIDJF77L","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"pith_short_8","alias_value":"SNVMO3T4","created_at":"2026-07-05T06:55:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SNVMO3T4AIDJF77LGVH5YC2PMT","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-28T15:18:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"cc977a35a293fe022e077f3e6bf1281e8d6093ae7dd0a5670ae3cdbd40904c46","abstract_canon_sha256":"8c618ee8b31c2adea1cb809922cd06e751daa79a71229e33e3f7266be1849ba1"},"schema_version":"1.0"},"canonical_sha256":"936ac76e7c020692ffeb354fdc0b4f64fe4dce12a1e3bdaabd23ba9dd9f70a91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:17.679370Z","signature_b64":"G2Nx83uwZqtb11wyO/zXDP1DWGM5jdSbWifaUn2Cd/gqjqDymCTo7OAD6t1Fuo71zPgAH7NtSqJhGjBpVabjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"936ac76e7c020692ffeb354fdc0b4f64fe4dce12a1e3bdaabd23ba9dd9f70a91","last_reissued_at":"2026-07-05T06:55:17.678819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:17.678819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16511","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":"2026-07-05T06:55:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YcXWntjVYoG0KavZ+MGhbeMmm7e3l6UrfoaszZgZmvCEH6C5gPwctkImLZ+5G7ZviHtOPHv87vHgzUjDX7cSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:04:25.628356Z"},"content_sha256":"639ff06a64e454a4d9a73586c268acf070d7522943e28ebd8459a0577df82bef","schema_version":"1.0","event_id":"sha256:639ff06a64e454a4d9a73586c268acf070d7522943e28ebd8459a0577df82bef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SNVMO3T4AIDJF77LGVH5YC2PMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toloka Visual Question Answering Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Alisa Smirnova, Daniil Likhobaba, Dmitry Ustalov, Nikita Pavlichenko, Sergey Koshelev","submitted_at":"2023-09-28T15:18:35Z","abstract_excerpt":"In this paper, we present Toloka Visual Question Answering, a new crowdsourced dataset allowing comparing performance of machine learning systems against human level of expertise in the grounding visual question answering task. In this task, given an image and a textual question, one has to draw the bounding box around the object correctly responding to that question. Every image-question pair contains the response, with only one correct response per image. Our dataset contains 45,199 pairs of images and questions in English, provided with ground truth bounding boxes, split into train and two "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16511","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/2309.16511/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":"2026-07-05T06:55:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VvFjYlNeVpHdUaLvViD8tBSR2W1MbGdzlw/ti7Bj5lZrnI7mMJAQZl2gVQar0Y+M0dd8kYVRTTK/gl4j985wDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:04:25.628742Z"},"content_sha256":"74e89293ceaa47f7c186983115bc3e958038aeac80d05f783d0c42e47cfcb12c","schema_version":"1.0","event_id":"sha256:74e89293ceaa47f7c186983115bc3e958038aeac80d05f783d0c42e47cfcb12c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNVMO3T4AIDJF77LGVH5YC2PMT/bundle.json","state_url":"https://pith.science/pith/SNVMO3T4AIDJF77LGVH5YC2PMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNVMO3T4AIDJF77LGVH5YC2PMT/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":"2026-08-06T05:04:25Z","links":{"resolver":"https://pith.science/pith/SNVMO3T4AIDJF77LGVH5YC2PMT","bundle":"https://pith.science/pith/SNVMO3T4AIDJF77LGVH5YC2PMT/bundle.json","state":"https://pith.science/pith/SNVMO3T4AIDJF77LGVH5YC2PMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNVMO3T4AIDJF77LGVH5YC2PMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SNVMO3T4AIDJF77LGVH5YC2PMT","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":"8c618ee8b31c2adea1cb809922cd06e751daa79a71229e33e3f7266be1849ba1","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-28T15:18:35Z","title_canon_sha256":"cc977a35a293fe022e077f3e6bf1281e8d6093ae7dd0a5670ae3cdbd40904c46"},"schema_version":"1.0","source":{"id":"2309.16511","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16511","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16511v1","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16511","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"pith_short_12","alias_value":"SNVMO3T4AIDJ","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"pith_short_16","alias_value":"SNVMO3T4AIDJF77L","created_at":"2026-07-05T06:55:17Z"},{"alias_kind":"pith_short_8","alias_value":"SNVMO3T4","created_at":"2026-07-05T06:55:17Z"}],"graph_snapshots":[{"event_id":"sha256:74e89293ceaa47f7c186983115bc3e958038aeac80d05f783d0c42e47cfcb12c","target":"graph","created_at":"2026-07-05T06:55:17Z","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/2309.16511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present Toloka Visual Question Answering, a new crowdsourced dataset allowing comparing performance of machine learning systems against human level of expertise in the grounding visual question answering task. In this task, given an image and a textual question, one has to draw the bounding box around the object correctly responding to that question. Every image-question pair contains the response, with only one correct response per image. Our dataset contains 45,199 pairs of images and questions in English, provided with ground truth bounding boxes, split into train and two ","authors_text":"Alisa Smirnova, Daniil Likhobaba, Dmitry Ustalov, Nikita Pavlichenko, Sergey Koshelev","cross_cats":["cs.AI","cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-28T15:18:35Z","title":"Toloka Visual Question Answering Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16511","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":"sha256:639ff06a64e454a4d9a73586c268acf070d7522943e28ebd8459a0577df82bef","target":"record","created_at":"2026-07-05T06:55:17Z","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":"8c618ee8b31c2adea1cb809922cd06e751daa79a71229e33e3f7266be1849ba1","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-28T15:18:35Z","title_canon_sha256":"cc977a35a293fe022e077f3e6bf1281e8d6093ae7dd0a5670ae3cdbd40904c46"},"schema_version":"1.0","source":{"id":"2309.16511","kind":"arxiv","version":1}},"canonical_sha256":"936ac76e7c020692ffeb354fdc0b4f64fe4dce12a1e3bdaabd23ba9dd9f70a91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"936ac76e7c020692ffeb354fdc0b4f64fe4dce12a1e3bdaabd23ba9dd9f70a91","first_computed_at":"2026-07-05T06:55:17.678819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:17.678819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G2Nx83uwZqtb11wyO/zXDP1DWGM5jdSbWifaUn2Cd/gqjqDymCTo7OAD6t1Fuo71zPgAH7NtSqJhGjBpVabjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:17.679370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16511","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:639ff06a64e454a4d9a73586c268acf070d7522943e28ebd8459a0577df82bef","sha256:74e89293ceaa47f7c186983115bc3e958038aeac80d05f783d0c42e47cfcb12c"],"state_sha256":"33463398ac50fe5f699c487cc92b4001632312339a3ba23cd73546d83b5ab5c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFNXh9kwGLLGW6JsjNwuVZ9/5nNGU/SWQStEKLkAz7F4iNimOqRIHyRjy8HjIVZPwwfEzjwb3FQl5CRAxovnBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:04:25.632355Z","bundle_sha256":"c4dec4ef2d3e20500fcb090a81cee3ae067e79a11b812977dcc0b4fd1c8e816f"}}