{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6TVDS74D3FERNYRFEQWMOMJMXP","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":"35f6bd35d383bfc85f96dc3b401847a4beb8d633fde6c5d40d8d2b98c3d3c243","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-29T14:30:57Z","title_canon_sha256":"155a0e3eca0304df443b04d946ab0969dbd4cf3a3be9c687f2906c0c54af1067"},"schema_version":"1.0","source":{"id":"2004.14231","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14231","created_at":"2026-07-05T01:39:57Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14231v2","created_at":"2026-07-05T01:39:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14231","created_at":"2026-07-05T01:39:57Z"},{"alias_kind":"pith_short_12","alias_value":"6TVDS74D3FER","created_at":"2026-07-05T01:39:57Z"},{"alias_kind":"pith_short_16","alias_value":"6TVDS74D3FERNYRF","created_at":"2026-07-05T01:39:57Z"},{"alias_kind":"pith_short_8","alias_value":"6TVDS74D","created_at":"2026-07-05T01:39:57Z"}],"graph_snapshots":[{"event_id":"sha256:f80ef0409842beeef92e668b566d6778f346f64c30f8f9a1caff04fd19410825","target":"graph","created_at":"2026-07-05T01:39:57Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.14231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic captioning of images is a task that combines the challenges of image analysis and text generation. One important aspect in captioning is the notion of attention: How to decide what to describe and in which order. Inspired by the successes in text analysis and translation, previous work have proposed the \\textit{transformer} architecture for image captioning. However, the structure between the \\textit{semantic units} in images (usually the detected regions from object detection model) and sentences (each single word) is different. Limited work has been done to adapt the transformer's ","authors_text":"Bodo Rosenhahn, Hamed R. Tavakoli, Michael Yang, Nicolas Pugeault, Sen He, Wentong Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-29T14:30:57Z","title":"Image Captioning through Image Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14231","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":"sha256:7f09a078b7c76d9366422582637ff9fb259cb76dd08943c6fc62593ace07c42f","target":"record","created_at":"2026-07-05T01:39:57Z","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":"35f6bd35d383bfc85f96dc3b401847a4beb8d633fde6c5d40d8d2b98c3d3c243","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-29T14:30:57Z","title_canon_sha256":"155a0e3eca0304df443b04d946ab0969dbd4cf3a3be9c687f2906c0c54af1067"},"schema_version":"1.0","source":{"id":"2004.14231","kind":"arxiv","version":2}},"canonical_sha256":"f4ea397f83d94916e225242cc7312cbbce8fef57f42ed218c8f64543c9455378","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4ea397f83d94916e225242cc7312cbbce8fef57f42ed218c8f64543c9455378","first_computed_at":"2026-07-05T01:39:57.840436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:57.840436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nUtyLWSl1PZo7ErUjmeU3pGdSA8Y42YjReS04p66sGnXCDn+OtsvJwH3FDTmsfCkrURqNT+GZHh3biGtuPZpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:57.840902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14231","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f09a078b7c76d9366422582637ff9fb259cb76dd08943c6fc62593ace07c42f","sha256:f80ef0409842beeef92e668b566d6778f346f64c30f8f9a1caff04fd19410825"],"state_sha256":"deee05d577d9bac2f20f326a9a022482a9f0c8cc76cc46ccb22a9ae00ca362ee"}