{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IIGRTC224HLTQZFW35ZHE7NEPB","short_pith_number":"pith:IIGRTC22","canonical_record":{"source":{"id":"1606.03556","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-11T05:41:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d23bc869d0c98cda43d1be017143ea98bdef3a866179894440d14ff34243b503","abstract_canon_sha256":"ab16448293992d7b6e119da88c6964cb16c32c8a983c2696c53a6310f8c0c278"},"schema_version":"1.0"},"canonical_sha256":"420d198b5ae1d73864b6df72727da478654f746389498c00199b90b4c085afd8","source":{"kind":"arxiv","id":"1606.03556","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03556","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03556v2","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03556","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"IIGRTC224HLT","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IIGRTC224HLTQZFW","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IIGRTC22","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IIGRTC224HLTQZFW35ZHE7NEPB","target":"record","payload":{"canonical_record":{"source":{"id":"1606.03556","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-11T05:41:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d23bc869d0c98cda43d1be017143ea98bdef3a866179894440d14ff34243b503","abstract_canon_sha256":"ab16448293992d7b6e119da88c6964cb16c32c8a983c2696c53a6310f8c0c278"},"schema_version":"1.0"},"canonical_sha256":"420d198b5ae1d73864b6df72727da478654f746389498c00199b90b4c085afd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:19.663966Z","signature_b64":"GN99tVTTQQvbK8rpY+y0uUEfcNv2r+onhnCMmsHK4LulkyxZ+ruC9gIyjbj8CoX+qEamBTbjFqH/VkwYAHEWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"420d198b5ae1d73864b6df72727da478654f746389498c00199b90b4c085afd8","last_reissued_at":"2026-05-18T01:12:19.663590Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:19.663590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.03556","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":"2026-05-18T01:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T0Yr9yuCCajYOK9JjKtn+m+oapTW6AOStTU1sCsau0mnJaAtwhsPgeAY3fYcLhFyNGytbyzClVZppzolH6vSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:10:32.339007Z"},"content_sha256":"9d5e5044c865dac8a64e33827f4810826265bce60a84e7b7659905d0a04681fd","schema_version":"1.0","event_id":"sha256:9d5e5044c865dac8a64e33827f4810826265bce60a84e7b7659905d0a04681fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IIGRTC224HLTQZFW35ZHE7NEPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhishek Das, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra, Harsh Agrawal","submitted_at":"2016-06-11T05:41:10Z","abstract_excerpt":"We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a question. Thus, we introduce the VQA-HAT (Human ATtention) dataset. We evaluate attention maps generated by state-of-the-art VQA models against human attention both qualitatively (via visualizations) and quantitatively (via rank-order correlation). Overall, our experiments show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03556","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":""},"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":"2026-05-18T01:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2FQoN31RUO/zmE8YjFeSlhlOqlQb9Dga/53jKbAap4LSlwh+xC4p+0EzqgomKCFM32WlwdXM6SIzPkANtZDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:10:32.339367Z"},"content_sha256":"613500aee15ffccd3460d076c64650a9a75d41f768985a23254054e16f8a3e39","schema_version":"1.0","event_id":"sha256:613500aee15ffccd3460d076c64650a9a75d41f768985a23254054e16f8a3e39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIGRTC224HLTQZFW35ZHE7NEPB/bundle.json","state_url":"https://pith.science/pith/IIGRTC224HLTQZFW35ZHE7NEPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIGRTC224HLTQZFW35ZHE7NEPB/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":"2026-06-01T19:10:32Z","links":{"resolver":"https://pith.science/pith/IIGRTC224HLTQZFW35ZHE7NEPB","bundle":"https://pith.science/pith/IIGRTC224HLTQZFW35ZHE7NEPB/bundle.json","state":"https://pith.science/pith/IIGRTC224HLTQZFW35ZHE7NEPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIGRTC224HLTQZFW35ZHE7NEPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IIGRTC224HLTQZFW35ZHE7NEPB","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":"ab16448293992d7b6e119da88c6964cb16c32c8a983c2696c53a6310f8c0c278","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-11T05:41:10Z","title_canon_sha256":"d23bc869d0c98cda43d1be017143ea98bdef3a866179894440d14ff34243b503"},"schema_version":"1.0","source":{"id":"1606.03556","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03556","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03556v2","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03556","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"IIGRTC224HLT","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IIGRTC224HLTQZFW","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IIGRTC22","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:613500aee15ffccd3460d076c64650a9a75d41f768985a23254054e16f8a3e39","target":"graph","created_at":"2026-05-18T01:12:19Z","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"},"paper":{"abstract_excerpt":"We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a question. Thus, we introduce the VQA-HAT (Human ATtention) dataset. We evaluate attention maps generated by state-of-the-art VQA models against human attention both qualitatively (via visualizations) and quantitatively (via rank-order correlation). Overall, our experiments show tha","authors_text":"Abhishek Das, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra, Harsh Agrawal","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-11T05:41:10Z","title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03556","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":"sha256:9d5e5044c865dac8a64e33827f4810826265bce60a84e7b7659905d0a04681fd","target":"record","created_at":"2026-05-18T01:12:19Z","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":"ab16448293992d7b6e119da88c6964cb16c32c8a983c2696c53a6310f8c0c278","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-11T05:41:10Z","title_canon_sha256":"d23bc869d0c98cda43d1be017143ea98bdef3a866179894440d14ff34243b503"},"schema_version":"1.0","source":{"id":"1606.03556","kind":"arxiv","version":2}},"canonical_sha256":"420d198b5ae1d73864b6df72727da478654f746389498c00199b90b4c085afd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"420d198b5ae1d73864b6df72727da478654f746389498c00199b90b4c085afd8","first_computed_at":"2026-05-18T01:12:19.663590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:19.663590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GN99tVTTQQvbK8rpY+y0uUEfcNv2r+onhnCMmsHK4LulkyxZ+ruC9gIyjbj8CoX+qEamBTbjFqH/VkwYAHEWBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:19.663966Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.03556","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d5e5044c865dac8a64e33827f4810826265bce60a84e7b7659905d0a04681fd","sha256:613500aee15ffccd3460d076c64650a9a75d41f768985a23254054e16f8a3e39"],"state_sha256":"a0b6af0c032739ed325351e37ac68ec68a44047c13af4955d292c51348fda21c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xXNfREH/ySx5fOzu9dyIMBoGXDh/nIOQu1C2/zLRN0e/DBsmgJ/SGiLNU/raEzISrQ9lwXoFrjZvMAEf1JcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T19:10:32.341253Z","bundle_sha256":"6f2afc6aaa31372ab6cb798d6240acd2437b8feef7a6183a1e44e6048f347de5"}}