{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:IVERX76V3NYYTTHZKTHXFOO7NK","short_pith_number":"pith:IVERX76V","canonical_record":{"source":{"id":"1511.03416","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-11T08:29:14Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"6087622bed02159c65219f97ae4174cf513474a34df318d3542ba4518378965e","abstract_canon_sha256":"c35dcb30533929178c4c8d0d7d608be8cdc37d5cc32efa601b9db47a03997070"},"schema_version":"1.0"},"canonical_sha256":"45491bffd5db7189ccf954cf72b9df6a86d4861c85b0e4ee68c5b40460b11147","source":{"kind":"arxiv","id":"1511.03416","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.03416","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"1511.03416v4","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03416","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"IVERX76V3NYY","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IVERX76V3NYYTTHZ","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IVERX76V","created_at":"2026-05-18T12:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:IVERX76V3NYYTTHZKTHXFOO7NK","target":"record","payload":{"canonical_record":{"source":{"id":"1511.03416","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-11T08:29:14Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"6087622bed02159c65219f97ae4174cf513474a34df318d3542ba4518378965e","abstract_canon_sha256":"c35dcb30533929178c4c8d0d7d608be8cdc37d5cc32efa601b9db47a03997070"},"schema_version":"1.0"},"canonical_sha256":"45491bffd5db7189ccf954cf72b9df6a86d4861c85b0e4ee68c5b40460b11147","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:25.064434Z","signature_b64":"LzJGDIDF74pJrnUljLpdXqOWMn2cyLm9DUveg4Fp4wC8nnbLFwSEeicymQJD4WSMf2djipFrcp0x7uu5eSkgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45491bffd5db7189ccf954cf72b9df6a86d4861c85b0e4ee68c5b40460b11147","last_reissued_at":"2026-05-18T01:17:25.063885Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:25.063885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.03416","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":"2026-05-18T01:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u53sI+PlBtl7G9VKM/95JAUXOK7QidKa+AQfwKJIt96O3I3d4jOXwp6pHbAbqfJh3krHM+MAKCHvJAvJR+UWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:23:55.785069Z"},"content_sha256":"a9339dc7c2235d39b7bfd59e64e257b970d02903cfd192bcfbf9e2d73263b119","schema_version":"1.0","event_id":"sha256:a9339dc7c2235d39b7bfd59e64e257b970d02903cfd192bcfbf9e2d73263b119"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:IVERX76V3NYYTTHZKTHXFOO7NK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual7W: Grounded Question Answering in Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Li Fei-Fei, Michael Bernstein, Oliver Groth, Yuke Zhu","submitted_at":"2015-11-11T08:29:14Z","abstract_excerpt":"We have seen great progress in basic perceptual tasks such as object recognition and detection. However, AI models still fail to match humans in high-level vision tasks due to the lack of capacities for deeper reasoning. Recently the new task of visual question answering (QA) has been proposed to evaluate a model's capacity for deep image understanding. Previous works have established a loose, global association between QA sentences and images. However, many questions and answers, in practice, relate to local regions in the images. We establish a semantic link between textual descriptions and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03416","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":""},"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":"2026-05-18T01:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mgp619yAS/wCQsQeWqZ5ImXqbdLQVZvl+U0n9rQOMtosq3ygbrm69v4/1pqwN4XWIpgWbSwShHg0o7HvRA2uBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:23:55.785428Z"},"content_sha256":"4d5d2bfb04da24b8c750577d147a02d11afe136e3a06c67b9e960a6bae8136be","schema_version":"1.0","event_id":"sha256:4d5d2bfb04da24b8c750577d147a02d11afe136e3a06c67b9e960a6bae8136be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVERX76V3NYYTTHZKTHXFOO7NK/bundle.json","state_url":"https://pith.science/pith/IVERX76V3NYYTTHZKTHXFOO7NK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVERX76V3NYYTTHZKTHXFOO7NK/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":"2026-06-08T23:23:55Z","links":{"resolver":"https://pith.science/pith/IVERX76V3NYYTTHZKTHXFOO7NK","bundle":"https://pith.science/pith/IVERX76V3NYYTTHZKTHXFOO7NK/bundle.json","state":"https://pith.science/pith/IVERX76V3NYYTTHZKTHXFOO7NK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVERX76V3NYYTTHZKTHXFOO7NK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:IVERX76V3NYYTTHZKTHXFOO7NK","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":"c35dcb30533929178c4c8d0d7d608be8cdc37d5cc32efa601b9db47a03997070","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-11T08:29:14Z","title_canon_sha256":"6087622bed02159c65219f97ae4174cf513474a34df318d3542ba4518378965e"},"schema_version":"1.0","source":{"id":"1511.03416","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.03416","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"1511.03416v4","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03416","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"IVERX76V3NYY","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IVERX76V3NYYTTHZ","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IVERX76V","created_at":"2026-05-18T12:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:4d5d2bfb04da24b8c750577d147a02d11afe136e3a06c67b9e960a6bae8136be","target":"graph","created_at":"2026-05-18T01:17:25Z","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"},"paper":{"abstract_excerpt":"We have seen great progress in basic perceptual tasks such as object recognition and detection. However, AI models still fail to match humans in high-level vision tasks due to the lack of capacities for deeper reasoning. Recently the new task of visual question answering (QA) has been proposed to evaluate a model's capacity for deep image understanding. Previous works have established a loose, global association between QA sentences and images. However, many questions and answers, in practice, relate to local regions in the images. We establish a semantic link between textual descriptions and ","authors_text":"Li Fei-Fei, Michael Bernstein, Oliver Groth, Yuke Zhu","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-11T08:29:14Z","title":"Visual7W: Grounded Question Answering in Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03416","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:a9339dc7c2235d39b7bfd59e64e257b970d02903cfd192bcfbf9e2d73263b119","target":"record","created_at":"2026-05-18T01:17:25Z","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":"c35dcb30533929178c4c8d0d7d608be8cdc37d5cc32efa601b9db47a03997070","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-11T08:29:14Z","title_canon_sha256":"6087622bed02159c65219f97ae4174cf513474a34df318d3542ba4518378965e"},"schema_version":"1.0","source":{"id":"1511.03416","kind":"arxiv","version":4}},"canonical_sha256":"45491bffd5db7189ccf954cf72b9df6a86d4861c85b0e4ee68c5b40460b11147","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45491bffd5db7189ccf954cf72b9df6a86d4861c85b0e4ee68c5b40460b11147","first_computed_at":"2026-05-18T01:17:25.063885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:25.063885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LzJGDIDF74pJrnUljLpdXqOWMn2cyLm9DUveg4Fp4wC8nnbLFwSEeicymQJD4WSMf2djipFrcp0x7uu5eSkgBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:25.064434Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.03416","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9339dc7c2235d39b7bfd59e64e257b970d02903cfd192bcfbf9e2d73263b119","sha256:4d5d2bfb04da24b8c750577d147a02d11afe136e3a06c67b9e960a6bae8136be"],"state_sha256":"97de7eb0074681d9e5f21953d51ffca60af45d014b32d8de87512fa59bd739d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KPfVGdwXQyAcLNvMYSCI2c3RMbyAlZWmyEUFXVKaE49zCaaWcI8iy8QDCgcgV1LH5RN6RNTZ5+e1CNX9hZTPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T23:23:55.787313Z","bundle_sha256":"e839d7a4138925f4ca6e523aaf8f13f0bd260c28fdb1db50346bad22baf6d71b"}}