{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZDA2APCCZ4MVTCYYIVTMUDEVXR","short_pith_number":"pith:ZDA2APCC","canonical_record":{"source":{"id":"1702.06700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-22T08:19:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.NE"],"title_canon_sha256":"3b72f7d0b76759df5f213a931068cf0a246c8160de7eb4a20b1fdb18a4cdc0a8","abstract_canon_sha256":"b3b260cba32e2628e0c6d28288597e77161869bee939a30605e1462a6c3cf93b"},"schema_version":"1.0"},"canonical_sha256":"c8c1a03c42cf19598b184566ca0c95bc4f993ab05b960d802993389f4b5aebb1","source":{"kind":"arxiv","id":"1702.06700","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06700","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06700v1","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06700","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZDA2APCCZ4MV","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZDA2APCCZ4MVTCYY","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZDA2APCC","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZDA2APCCZ4MVTCYYIVTMUDEVXR","target":"record","payload":{"canonical_record":{"source":{"id":"1702.06700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-22T08:19:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.NE"],"title_canon_sha256":"3b72f7d0b76759df5f213a931068cf0a246c8160de7eb4a20b1fdb18a4cdc0a8","abstract_canon_sha256":"b3b260cba32e2628e0c6d28288597e77161869bee939a30605e1462a6c3cf93b"},"schema_version":"1.0"},"canonical_sha256":"c8c1a03c42cf19598b184566ca0c95bc4f993ab05b960d802993389f4b5aebb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:12.893772Z","signature_b64":"eqDF+VOBqfkAmbw2egZElIZPtejJ7Hp3zc02RyxjpDyNSs82exC7bSP2uBMosyFwGQD6I6aCuCTV7PzOUXbUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c1a03c42cf19598b184566ca0c95bc4f993ab05b960d802993389f4b5aebb1","last_reissued_at":"2026-05-18T00:50:12.893343Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:12.893343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.06700","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":"2026-05-18T00:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I7dK0oJKuzUXRtytpe9sB6OsZpXvQZyzhmp052RJyty3z6eq5aKx1n5J71sE0tkfeynDwvpS+sITlA77ihN7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T03:29:51.587629Z"},"content_sha256":"cb18e9eee112182df6a7622f2b75497ae8f27e1f8cea17658e2cefd00356537e","schema_version":"1.0","event_id":"sha256:cb18e9eee112182df6a7622f2b75497ae8f27e1f8cea17658e2cefd00356537e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZDA2APCCZ4MVTCYYIVTMUDEVXR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-driven Visual Saliency and Attention-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.NE"],"primary_cat":"cs.CV","authors_text":"Donghui Wang, Yuetan Lin, Yueting Zhuang, Zhangyang Pang","submitted_at":"2017-02-22T08:19:38Z","abstract_excerpt":"Visual question answering (VQA) has witnessed great progress since May, 2015 as a classic problem unifying visual and textual data into a system. Many enlightening VQA works explore deep into the image and question encodings and fusing methods, of which attention is the most effective and infusive mechanism. Current attention based methods focus on adequate fusion of visual and textual features, but lack the attention to where people focus to ask questions about the image. Traditional attention based methods attach a single value to the feature at each spatial location, which losses many usefu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06700","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":""},"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":"2026-05-18T00:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ylu11+A7IbJmAQ4OfsvD70egnpMFaouhw/9nlNMbuMjd2WQUmudCMzmEd7wx/PbWR9qkLNwx6IwwOt15EvLtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T03:29:51.587991Z"},"content_sha256":"db0d2e744b423618017457a8385958e7acd5f2f56d6434219a54c588d554648c","schema_version":"1.0","event_id":"sha256:db0d2e744b423618017457a8385958e7acd5f2f56d6434219a54c588d554648c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDA2APCCZ4MVTCYYIVTMUDEVXR/bundle.json","state_url":"https://pith.science/pith/ZDA2APCCZ4MVTCYYIVTMUDEVXR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDA2APCCZ4MVTCYYIVTMUDEVXR/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":"2026-05-30T03:29:51Z","links":{"resolver":"https://pith.science/pith/ZDA2APCCZ4MVTCYYIVTMUDEVXR","bundle":"https://pith.science/pith/ZDA2APCCZ4MVTCYYIVTMUDEVXR/bundle.json","state":"https://pith.science/pith/ZDA2APCCZ4MVTCYYIVTMUDEVXR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDA2APCCZ4MVTCYYIVTMUDEVXR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZDA2APCCZ4MVTCYYIVTMUDEVXR","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":"b3b260cba32e2628e0c6d28288597e77161869bee939a30605e1462a6c3cf93b","cross_cats_sorted":["cs.AI","cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-22T08:19:38Z","title_canon_sha256":"3b72f7d0b76759df5f213a931068cf0a246c8160de7eb4a20b1fdb18a4cdc0a8"},"schema_version":"1.0","source":{"id":"1702.06700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06700","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06700v1","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06700","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZDA2APCCZ4MV","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZDA2APCCZ4MVTCYY","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZDA2APCC","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:db0d2e744b423618017457a8385958e7acd5f2f56d6434219a54c588d554648c","target":"graph","created_at":"2026-05-18T00:50:12Z","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":"Visual question answering (VQA) has witnessed great progress since May, 2015 as a classic problem unifying visual and textual data into a system. Many enlightening VQA works explore deep into the image and question encodings and fusing methods, of which attention is the most effective and infusive mechanism. Current attention based methods focus on adequate fusion of visual and textual features, but lack the attention to where people focus to ask questions about the image. Traditional attention based methods attach a single value to the feature at each spatial location, which losses many usefu","authors_text":"Donghui Wang, Yuetan Lin, Yueting Zhuang, Zhangyang Pang","cross_cats":["cs.AI","cs.CL","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-22T08:19:38Z","title":"Task-driven Visual Saliency and Attention-based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06700","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:cb18e9eee112182df6a7622f2b75497ae8f27e1f8cea17658e2cefd00356537e","target":"record","created_at":"2026-05-18T00:50:12Z","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":"b3b260cba32e2628e0c6d28288597e77161869bee939a30605e1462a6c3cf93b","cross_cats_sorted":["cs.AI","cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-22T08:19:38Z","title_canon_sha256":"3b72f7d0b76759df5f213a931068cf0a246c8160de7eb4a20b1fdb18a4cdc0a8"},"schema_version":"1.0","source":{"id":"1702.06700","kind":"arxiv","version":1}},"canonical_sha256":"c8c1a03c42cf19598b184566ca0c95bc4f993ab05b960d802993389f4b5aebb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8c1a03c42cf19598b184566ca0c95bc4f993ab05b960d802993389f4b5aebb1","first_computed_at":"2026-05-18T00:50:12.893343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:12.893343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eqDF+VOBqfkAmbw2egZElIZPtejJ7Hp3zc02RyxjpDyNSs82exC7bSP2uBMosyFwGQD6I6aCuCTV7PzOUXbUCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:12.893772Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.06700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb18e9eee112182df6a7622f2b75497ae8f27e1f8cea17658e2cefd00356537e","sha256:db0d2e744b423618017457a8385958e7acd5f2f56d6434219a54c588d554648c"],"state_sha256":"e988681b8fdd53cdd7682877ab17a7be2ae62d2ba654cf5dee3c3b64e0c24d05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AS+ewD5xLxxBZT7uuXTFmRlXNlBF9XFSkWEBPIvuETsquho8IbzzDqZGqA3gYNTt/bnxBr2VWZzlqY91g9WRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T03:29:51.590102Z","bundle_sha256":"25f5b4e9efd085811fdec0e2e0b5ed4d1d938bc9cce3089c9db962d8ec8a2a15"}}