{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LVK7KCOHO5STN7ATMGVNCHLC2X","short_pith_number":"pith:LVK7KCOH","canonical_record":{"source":{"id":"2302.11713","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-23T00:33:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1508d56d6c35d78ff50f9d94db67931b20c0cc5ddd921ebefbdbc77afef4a7e8","abstract_canon_sha256":"747d3d4c6cde5e589cfa78ffef5307ccfaa8df7fa03a98f7bf982f7f38a28eac"},"schema_version":"1.0"},"canonical_sha256":"5d55f509c7776536fc1361aad11d62d5ecbeed469181436a2dea9ec43e63d240","source":{"kind":"arxiv","id":"2302.11713","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11713","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11713v5","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11713","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"LVK7KCOHO5ST","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"LVK7KCOHO5STN7AT","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"LVK7KCOH","created_at":"2026-07-05T07:01:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LVK7KCOHO5STN7ATMGVNCHLC2X","target":"record","payload":{"canonical_record":{"source":{"id":"2302.11713","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-23T00:33:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1508d56d6c35d78ff50f9d94db67931b20c0cc5ddd921ebefbdbc77afef4a7e8","abstract_canon_sha256":"747d3d4c6cde5e589cfa78ffef5307ccfaa8df7fa03a98f7bf982f7f38a28eac"},"schema_version":"1.0"},"canonical_sha256":"5d55f509c7776536fc1361aad11d62d5ecbeed469181436a2dea9ec43e63d240","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:39.570874Z","signature_b64":"/3+Jp8FX8gCXQHgdPhdRBkgVX8ItQ9SSHDC/OUT8Ucnfb0IPd5LC89tjNgEpIZNexNdsaD5nxZpVBC9269QvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d55f509c7776536fc1361aad11d62d5ecbeed469181436a2dea9ec43e63d240","last_reissued_at":"2026-07-05T07:01:39.570394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:39.570394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.11713","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:01:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QAbYLh+ZfD2LwtRl/4g/b9qyG/771ty/VDgUzhCT29+WGLG5HNbEx4+rFQ+pEHLcSCfcqsvuC3s8RBA8kdHsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:50:21.009644Z"},"content_sha256":"07d22e0455ee62ab488671c0e2d9ae674c3845f8a63031c6f0ae0217609b9d7a","schema_version":"1.0","event_id":"sha256:07d22e0455ee62ab488671c0e2d9ae674c3845f8a63031c6f0ae0217609b9d7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LVK7KCOHO5STN7ATMGVNCHLC2X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Alan Ritter, Haitian Sun, Hexiang Hu, Ming-Wei Chang, Soravit Changpinyo, Yang Chen, Yi Luan","submitted_at":"2023-02-23T00:33:54Z","abstract_excerpt":"Pre-trained vision and language models have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering. However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual content but knowledge-intensive and information-seeking. In this study, we introduce InfoSeek, a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge. Using InfoSeek, we analyze various pre-trained visual question answeri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11713","kind":"arxiv","version":5},"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/2302.11713/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":"2026-07-05T07:01:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ORx9CdbeiCADtLrE+uACO8Mr29OLSAs/QuI6+qiKojqCER6wBvm+6u3zwRiv5Dsrj4rU8Z5wZclYxPZxOhlNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:50:21.010042Z"},"content_sha256":"1596cbf7e59359a21500cdf8a6a7b78a8594e7433267800e097d70ab8d202963","schema_version":"1.0","event_id":"sha256:1596cbf7e59359a21500cdf8a6a7b78a8594e7433267800e097d70ab8d202963"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LVK7KCOHO5STN7ATMGVNCHLC2X/bundle.json","state_url":"https://pith.science/pith/LVK7KCOHO5STN7ATMGVNCHLC2X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LVK7KCOHO5STN7ATMGVNCHLC2X/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":"2026-07-07T14:50:21Z","links":{"resolver":"https://pith.science/pith/LVK7KCOHO5STN7ATMGVNCHLC2X","bundle":"https://pith.science/pith/LVK7KCOHO5STN7ATMGVNCHLC2X/bundle.json","state":"https://pith.science/pith/LVK7KCOHO5STN7ATMGVNCHLC2X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LVK7KCOHO5STN7ATMGVNCHLC2X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LVK7KCOHO5STN7ATMGVNCHLC2X","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":"747d3d4c6cde5e589cfa78ffef5307ccfaa8df7fa03a98f7bf982f7f38a28eac","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-23T00:33:54Z","title_canon_sha256":"1508d56d6c35d78ff50f9d94db67931b20c0cc5ddd921ebefbdbc77afef4a7e8"},"schema_version":"1.0","source":{"id":"2302.11713","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11713","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11713v5","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11713","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"LVK7KCOHO5ST","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"LVK7KCOHO5STN7AT","created_at":"2026-07-05T07:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"LVK7KCOH","created_at":"2026-07-05T07:01:39Z"}],"graph_snapshots":[{"event_id":"sha256:1596cbf7e59359a21500cdf8a6a7b78a8594e7433267800e097d70ab8d202963","target":"graph","created_at":"2026-07-05T07:01:39Z","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/2302.11713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision and language models have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering. However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual content but knowledge-intensive and information-seeking. In this study, we introduce InfoSeek, a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge. Using InfoSeek, we analyze various pre-trained visual question answeri","authors_text":"Alan Ritter, Haitian Sun, Hexiang Hu, Ming-Wei Chang, Soravit Changpinyo, Yang Chen, Yi Luan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-23T00:33:54Z","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11713","kind":"arxiv","version":5},"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":"sha256:07d22e0455ee62ab488671c0e2d9ae674c3845f8a63031c6f0ae0217609b9d7a","target":"record","created_at":"2026-07-05T07:01:39Z","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":"747d3d4c6cde5e589cfa78ffef5307ccfaa8df7fa03a98f7bf982f7f38a28eac","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-23T00:33:54Z","title_canon_sha256":"1508d56d6c35d78ff50f9d94db67931b20c0cc5ddd921ebefbdbc77afef4a7e8"},"schema_version":"1.0","source":{"id":"2302.11713","kind":"arxiv","version":5}},"canonical_sha256":"5d55f509c7776536fc1361aad11d62d5ecbeed469181436a2dea9ec43e63d240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d55f509c7776536fc1361aad11d62d5ecbeed469181436a2dea9ec43e63d240","first_computed_at":"2026-07-05T07:01:39.570394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:39.570394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/3+Jp8FX8gCXQHgdPhdRBkgVX8ItQ9SSHDC/OUT8Ucnfb0IPd5LC89tjNgEpIZNexNdsaD5nxZpVBC9269QvCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:39.570874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.11713","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07d22e0455ee62ab488671c0e2d9ae674c3845f8a63031c6f0ae0217609b9d7a","sha256:1596cbf7e59359a21500cdf8a6a7b78a8594e7433267800e097d70ab8d202963"],"state_sha256":"3827d477e0caf09d01ce055502c2a60e8b0b0a5a36901143454741a72d926ae8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ytNqaYnJ40tyespbW8+V5KLEx6PDQqHEt3+Azl0+7Ex7l4L6YP5zu5tDu6SH3nQIGH/eFtRv/92kk2+lt4AAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:50:21.012175Z","bundle_sha256":"73ed8479f527e947c027e6c348f097b48f473eb28a803a9dfbaf759523f2a2ac"}}