{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:G5WZ4U3KO3UX7VS4K2SH4LXXMH","short_pith_number":"pith:G5WZ4U3K","canonical_record":{"source":{"id":"1603.02814","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-09T08:56:45Z","cross_cats_sorted":[],"title_canon_sha256":"8c7d3bbb3c84b4ee49cfa1e8124b6f6ace0dd2bd64b15d70467439e55ec2e80a","abstract_canon_sha256":"34aeec0f994bb5719cde0db7099dbba8808689bb03862265fab837b1eff564ee"},"schema_version":"1.0"},"canonical_sha256":"376d9e536a76e97fd65c56a47e2ef761fd0e13eff949b14a68653c653ca2f321","source":{"kind":"arxiv","id":"1603.02814","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.02814","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"1603.02814v2","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02814","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"G5WZ4U3KO3UX","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"G5WZ4U3KO3UX7VS4","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"G5WZ4U3K","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:G5WZ4U3KO3UX7VS4K2SH4LXXMH","target":"record","payload":{"canonical_record":{"source":{"id":"1603.02814","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-09T08:56:45Z","cross_cats_sorted":[],"title_canon_sha256":"8c7d3bbb3c84b4ee49cfa1e8124b6f6ace0dd2bd64b15d70467439e55ec2e80a","abstract_canon_sha256":"34aeec0f994bb5719cde0db7099dbba8808689bb03862265fab837b1eff564ee"},"schema_version":"1.0"},"canonical_sha256":"376d9e536a76e97fd65c56a47e2ef761fd0e13eff949b14a68653c653ca2f321","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:52.861259Z","signature_b64":"SOCBCh73ZHwuXY7XCqp3QTpFMK+KiKTo3RCvrzH96suwGmLUcgLiTYY6rf1ZdkALgPGLauLfcJJhL9j4jRpGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"376d9e536a76e97fd65c56a47e2ef761fd0e13eff949b14a68653c653ca2f321","last_reissued_at":"2026-05-18T00:54:52.860861Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:52.860861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.02814","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":"2026-05-18T00:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YoAGSZiNmhnP+VfLDl5sZuhmYzCQ7BnOJXxJmvNYiBPF0JxlTk3YNn7J7N40GlCtkxk6K8MQ09pbNqZbfEjvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:10:19.226233Z"},"content_sha256":"fc0b4312556f42b8ea25d5b8001dafa25ddc913baf22d5fad414fb79f6e226e9","schema_version":"1.0","event_id":"sha256:fc0b4312556f42b8ea25d5b8001dafa25ddc913baf22d5fad414fb79f6e226e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:G5WZ4U3KO3UX7VS4K2SH4LXXMH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Dick, Anton van den Hengel, Chunhua Shen, Peng Wang, Qi Wu","submitted_at":"2016-03-09T08:56:45Z","abstract_excerpt":"Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02814","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":"2026-05-18T00:54:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MemOLBi/Rdrfr0/cJzqY6kjN+luZTQ95ARSPbQ4K+y4qn3rpXiCCJ+OA4y7+rQ4wC3CunIDqDKV9dD63ZIomDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:10:19.226696Z"},"content_sha256":"8dd71796c5b7a8c52ec54d7c53c74520277af482df6646cff9d9bba56331cd64","schema_version":"1.0","event_id":"sha256:8dd71796c5b7a8c52ec54d7c53c74520277af482df6646cff9d9bba56331cd64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/bundle.json","state_url":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/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":"2026-08-09T22:10:19Z","links":{"resolver":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH","bundle":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/bundle.json","state":"https://pith.science/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5WZ4U3KO3UX7VS4K2SH4LXXMH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:G5WZ4U3KO3UX7VS4K2SH4LXXMH","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":"34aeec0f994bb5719cde0db7099dbba8808689bb03862265fab837b1eff564ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-09T08:56:45Z","title_canon_sha256":"8c7d3bbb3c84b4ee49cfa1e8124b6f6ace0dd2bd64b15d70467439e55ec2e80a"},"schema_version":"1.0","source":{"id":"1603.02814","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.02814","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"1603.02814v2","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02814","created_at":"2026-05-18T00:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"G5WZ4U3KO3UX","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"G5WZ4U3KO3UX7VS4","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"G5WZ4U3K","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:8dd71796c5b7a8c52ec54d7c53c74520277af482df6646cff9d9bba56331cd64","target":"graph","created_at":"2026-05-18T00:54:52Z","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":"Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism ca","authors_text":"Anthony Dick, Anton van den Hengel, Chunhua Shen, Peng Wang, Qi Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-09T08:56:45Z","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02814","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:fc0b4312556f42b8ea25d5b8001dafa25ddc913baf22d5fad414fb79f6e226e9","target":"record","created_at":"2026-05-18T00:54:52Z","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":"34aeec0f994bb5719cde0db7099dbba8808689bb03862265fab837b1eff564ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-09T08:56:45Z","title_canon_sha256":"8c7d3bbb3c84b4ee49cfa1e8124b6f6ace0dd2bd64b15d70467439e55ec2e80a"},"schema_version":"1.0","source":{"id":"1603.02814","kind":"arxiv","version":2}},"canonical_sha256":"376d9e536a76e97fd65c56a47e2ef761fd0e13eff949b14a68653c653ca2f321","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"376d9e536a76e97fd65c56a47e2ef761fd0e13eff949b14a68653c653ca2f321","first_computed_at":"2026-05-18T00:54:52.860861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:54:52.860861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SOCBCh73ZHwuXY7XCqp3QTpFMK+KiKTo3RCvrzH96suwGmLUcgLiTYY6rf1ZdkALgPGLauLfcJJhL9j4jRpGBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:54:52.861259Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.02814","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc0b4312556f42b8ea25d5b8001dafa25ddc913baf22d5fad414fb79f6e226e9","sha256:8dd71796c5b7a8c52ec54d7c53c74520277af482df6646cff9d9bba56331cd64"],"state_sha256":"7cc80ee6029140945439746d250b79378751e5ebb7048b6806c475382f06bac8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W1u/Ra/hDVpYdMVRUkNfdSbfBWwHRMvHXCILba02ZVA/+MeFKYTMSIhQ8sHyVephxxUntuTsUHWljVnp91aEAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:10:19.231542Z","bundle_sha256":"317d965c307e8e17b68f159dd65506aa95624be0a0e2b4e6a9a8fae3268bc302"}}