{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ORQMLU2EIC7FQUQIU25RHHFLH5","short_pith_number":"pith:ORQMLU2E","canonical_record":{"source":{"id":"1506.01144","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-03T07:06:11Z","cross_cats_sorted":[],"title_canon_sha256":"3ec1d262568e7198c7ccbebd0dc6d7d5be9c92057c8234acc6cdd2cf15dd5fad","abstract_canon_sha256":"c9a504f8196994bb8ffca4553fa337996c5fc8cb8b9f6ea71bbf833e6caef33c"},"schema_version":"1.0"},"canonical_sha256":"7460c5d34440be585208a6bb139cab3f4e76984c8e764f8ba137b5559eafe5dc","source":{"kind":"arxiv","id":"1506.01144","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.01144","created_at":"2026-05-18T01:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"1506.01144v6","created_at":"2026-05-18T01:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01144","created_at":"2026-05-18T01:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"ORQMLU2EIC7F","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"ORQMLU2EIC7FQUQI","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"ORQMLU2E","created_at":"2026-05-18T12:29:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ORQMLU2EIC7FQUQIU25RHHFLH5","target":"record","payload":{"canonical_record":{"source":{"id":"1506.01144","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-03T07:06:11Z","cross_cats_sorted":[],"title_canon_sha256":"3ec1d262568e7198c7ccbebd0dc6d7d5be9c92057c8234acc6cdd2cf15dd5fad","abstract_canon_sha256":"c9a504f8196994bb8ffca4553fa337996c5fc8cb8b9f6ea71bbf833e6caef33c"},"schema_version":"1.0"},"canonical_sha256":"7460c5d34440be585208a6bb139cab3f4e76984c8e764f8ba137b5559eafe5dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:07.224155Z","signature_b64":"rNf8ZcgpfZHui6jSER+3tgaL6hW+CQwTeNOXuHbGw8WBE0prIkJy7Jgfc3Kpxj/h4kL4AqFrT6c+rH8ENR16Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7460c5d34440be585208a6bb139cab3f4e76984c8e764f8ba137b5559eafe5dc","last_reissued_at":"2026-05-18T01:16:07.223250Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:07.223250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.01144","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jmDyXu0swC9Hp8xh/C6hOytUofdNFLw+AFallkgm4YEM7vuTjLgcS1dlSmkU9K3BEmebVOmzvTS+ddQfQ8DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:06:27.532153Z"},"content_sha256":"ce9481906e5bf9c393ea8cabb762323ce191b0562f9fc93825df8a4ea9d92390","schema_version":"1.0","event_id":"sha256:ce9481906e5bf9c393ea8cabb762323ce191b0562f9fc93825df8a4ea9d92390"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ORQMLU2EIC7FQUQIU25RHHFLH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What value do explicit high level concepts have in vision to language problems?","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, Lingqiao Liu, Qi Wu","submitted_at":"2015-06-03T07:06:11Z","abstract_excerpt":"Much of the recent progress in Vision-to-Language (V2L) 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. We propose here a method of incorporating high-level concepts into the very successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art performance in both image captioning and visual question answering. We also show that the same "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01144","kind":"arxiv","version":6},"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":"2026-05-18T01:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hOjBxiG3A2KGVtAaNirPgGqgQm6qXmshFj0Stq9KpGw9bs8USTrowhGFSPumIzNy8A79oku8DTymMKWmn0ccAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:06:27.532568Z"},"content_sha256":"7b8c5288ac60affd9436da243b0a3c088ada3f34de6855073b5ccdf36098991e","schema_version":"1.0","event_id":"sha256:7b8c5288ac60affd9436da243b0a3c088ada3f34de6855073b5ccdf36098991e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORQMLU2EIC7FQUQIU25RHHFLH5/bundle.json","state_url":"https://pith.science/pith/ORQMLU2EIC7FQUQIU25RHHFLH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORQMLU2EIC7FQUQIU25RHHFLH5/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":"2026-05-26T07:06:27Z","links":{"resolver":"https://pith.science/pith/ORQMLU2EIC7FQUQIU25RHHFLH5","bundle":"https://pith.science/pith/ORQMLU2EIC7FQUQIU25RHHFLH5/bundle.json","state":"https://pith.science/pith/ORQMLU2EIC7FQUQIU25RHHFLH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORQMLU2EIC7FQUQIU25RHHFLH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ORQMLU2EIC7FQUQIU25RHHFLH5","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":"c9a504f8196994bb8ffca4553fa337996c5fc8cb8b9f6ea71bbf833e6caef33c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-03T07:06:11Z","title_canon_sha256":"3ec1d262568e7198c7ccbebd0dc6d7d5be9c92057c8234acc6cdd2cf15dd5fad"},"schema_version":"1.0","source":{"id":"1506.01144","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.01144","created_at":"2026-05-18T01:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"1506.01144v6","created_at":"2026-05-18T01:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01144","created_at":"2026-05-18T01:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"ORQMLU2EIC7F","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"ORQMLU2EIC7FQUQI","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"ORQMLU2E","created_at":"2026-05-18T12:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:7b8c5288ac60affd9436da243b0a3c088ada3f34de6855073b5ccdf36098991e","target":"graph","created_at":"2026-05-18T01:16:07Z","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 of the recent progress in Vision-to-Language (V2L) 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. We propose here a method of incorporating high-level concepts into the very successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art performance in both image captioning and visual question answering. We also show that the same ","authors_text":"Anthony Dick, Anton van den Hengel, Chunhua Shen, Lingqiao Liu, Qi Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-03T07:06:11Z","title":"What value do explicit high level concepts have in vision to language problems?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01144","kind":"arxiv","version":6},"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:ce9481906e5bf9c393ea8cabb762323ce191b0562f9fc93825df8a4ea9d92390","target":"record","created_at":"2026-05-18T01:16:07Z","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":"c9a504f8196994bb8ffca4553fa337996c5fc8cb8b9f6ea71bbf833e6caef33c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-03T07:06:11Z","title_canon_sha256":"3ec1d262568e7198c7ccbebd0dc6d7d5be9c92057c8234acc6cdd2cf15dd5fad"},"schema_version":"1.0","source":{"id":"1506.01144","kind":"arxiv","version":6}},"canonical_sha256":"7460c5d34440be585208a6bb139cab3f4e76984c8e764f8ba137b5559eafe5dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7460c5d34440be585208a6bb139cab3f4e76984c8e764f8ba137b5559eafe5dc","first_computed_at":"2026-05-18T01:16:07.223250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:16:07.223250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rNf8ZcgpfZHui6jSER+3tgaL6hW+CQwTeNOXuHbGw8WBE0prIkJy7Jgfc3Kpxj/h4kL4AqFrT6c+rH8ENR16Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:16:07.224155Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.01144","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce9481906e5bf9c393ea8cabb762323ce191b0562f9fc93825df8a4ea9d92390","sha256:7b8c5288ac60affd9436da243b0a3c088ada3f34de6855073b5ccdf36098991e"],"state_sha256":"e015ae00f64eaf705b1b3e7c53fc5210f0819fec332d71fcaea9bc935fc71ee6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UCtbGVRydkGbCL2zGC+hNFMKy2frv3hAl2QAdjU0FGrZCcRKQwjazBgLNV/5ynkGg4iWEFTFUKnUjTXTUS8nDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:06:27.535036Z","bundle_sha256":"f641b01907f59dd125afa6d7b58217463c3c2c4247a53bf216231669cd9c9735"}}