{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:A7WTD53U7GRWLSLNYXUTLACQIR","short_pith_number":"pith:A7WTD53U","canonical_record":{"source":{"id":"1608.05203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-18T08:13:22Z","cross_cats_sorted":[],"title_canon_sha256":"3bc886db6bd513f7220a3a8cef24a98acd42761cb38c67215851cbf82e49f2ad","abstract_canon_sha256":"5a9de557c27f493de754ce3524a7c214553d6fc92eca5a43a0f41e4fe87bbe6f"},"schema_version":"1.0"},"canonical_sha256":"07ed31f774f9a365c96dc5e935805044540b21a11c78ff867c3f1ecdb61555f1","source":{"kind":"arxiv","id":"1608.05203","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05203","created_at":"2026-05-18T01:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05203v1","created_at":"2026-05-18T01:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05203","created_at":"2026-05-18T01:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"A7WTD53U7GRW","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"A7WTD53U7GRWLSLN","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"A7WTD53U","created_at":"2026-05-18T12:30:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:A7WTD53U7GRWLSLNYXUTLACQIR","target":"record","payload":{"canonical_record":{"source":{"id":"1608.05203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-18T08:13:22Z","cross_cats_sorted":[],"title_canon_sha256":"3bc886db6bd513f7220a3a8cef24a98acd42761cb38c67215851cbf82e49f2ad","abstract_canon_sha256":"5a9de557c27f493de754ce3524a7c214553d6fc92eca5a43a0f41e4fe87bbe6f"},"schema_version":"1.0"},"canonical_sha256":"07ed31f774f9a365c96dc5e935805044540b21a11c78ff867c3f1ecdb61555f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:31.626065Z","signature_b64":"9x8gTb+au8MYegHN/jgRjxjUxZIbNuqfYG40GTom/9hd0JUzORX8aI6Wpsr5n+hxVmIMbaMXKltTit6nVRiVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07ed31f774f9a365c96dc5e935805044540b21a11c78ff867c3f1ecdb61555f1","last_reissued_at":"2026-05-18T01:08:31.625485Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:31.625485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.05203","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":"2026-05-18T01:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VZkRQRFqXQ407R9mOUHJwrSLgbVSrxPkdlUMw3B5UUzsv9hDj5n3x19zA7q5esBjnBZMZwnVs+xtcK1Z0vuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T21:48:40.431707Z"},"content_sha256":"e4941337797e68ed32bfcca67d81d3d89645363db3421905847ea93205f67f53","schema_version":"1.0","event_id":"sha256:e4941337797e68ed32bfcca67d81d3d89645363db3421905847ea93205f67f53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:A7WTD53U7GRWLSLNYXUTLACQIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seeing with Humans: Gaze-Assisted Neural Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Bulling, Yusuke Sugano","submitted_at":"2016-08-18T08:13:22Z","abstract_excerpt":"Gaze reflects how humans process visual scenes and is therefore increasingly used in computer vision systems. Previous works demonstrated the potential of gaze for object-centric tasks, such as object localization and recognition, but it remains unclear if gaze can also be beneficial for scene-centric tasks, such as image captioning. We present a new perspective on gaze-assisted image captioning by studying the interplay between human gaze and the attention mechanism of deep neural networks. Using a public large-scale gaze dataset, we first assess the relationship between state-of-the-art obje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05203","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":"2026-05-18T01:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"evo9vmEe7yUCcNLRDXOZv8XGu3X5AsLiz+Lwe2GVJlziB0OGMUzRzHM0UL7U/V06AIC0pVHz/2mV8HVnyCuzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T21:48:40.432042Z"},"content_sha256":"d8fa3f1c5a12ff6a1d24e3958b36d659d3eb74b5c54cf8101cd71d163338231d","schema_version":"1.0","event_id":"sha256:d8fa3f1c5a12ff6a1d24e3958b36d659d3eb74b5c54cf8101cd71d163338231d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/bundle.json","state_url":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7WTD53U7GRWLSLNYXUTLACQIR/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":"2026-06-26T21:48:40Z","links":{"resolver":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR","bundle":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/bundle.json","state":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7WTD53U7GRWLSLNYXUTLACQIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:A7WTD53U7GRWLSLNYXUTLACQIR","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":"5a9de557c27f493de754ce3524a7c214553d6fc92eca5a43a0f41e4fe87bbe6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-18T08:13:22Z","title_canon_sha256":"3bc886db6bd513f7220a3a8cef24a98acd42761cb38c67215851cbf82e49f2ad"},"schema_version":"1.0","source":{"id":"1608.05203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.05203","created_at":"2026-05-18T01:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"1608.05203v1","created_at":"2026-05-18T01:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05203","created_at":"2026-05-18T01:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"A7WTD53U7GRW","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"A7WTD53U7GRWLSLN","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"A7WTD53U","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:d8fa3f1c5a12ff6a1d24e3958b36d659d3eb74b5c54cf8101cd71d163338231d","target":"graph","created_at":"2026-05-18T01:08:31Z","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":"Gaze reflects how humans process visual scenes and is therefore increasingly used in computer vision systems. Previous works demonstrated the potential of gaze for object-centric tasks, such as object localization and recognition, but it remains unclear if gaze can also be beneficial for scene-centric tasks, such as image captioning. We present a new perspective on gaze-assisted image captioning by studying the interplay between human gaze and the attention mechanism of deep neural networks. Using a public large-scale gaze dataset, we first assess the relationship between state-of-the-art obje","authors_text":"Andreas Bulling, Yusuke Sugano","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-18T08:13:22Z","title":"Seeing with Humans: Gaze-Assisted Neural Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05203","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:e4941337797e68ed32bfcca67d81d3d89645363db3421905847ea93205f67f53","target":"record","created_at":"2026-05-18T01:08:31Z","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":"5a9de557c27f493de754ce3524a7c214553d6fc92eca5a43a0f41e4fe87bbe6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-18T08:13:22Z","title_canon_sha256":"3bc886db6bd513f7220a3a8cef24a98acd42761cb38c67215851cbf82e49f2ad"},"schema_version":"1.0","source":{"id":"1608.05203","kind":"arxiv","version":1}},"canonical_sha256":"07ed31f774f9a365c96dc5e935805044540b21a11c78ff867c3f1ecdb61555f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07ed31f774f9a365c96dc5e935805044540b21a11c78ff867c3f1ecdb61555f1","first_computed_at":"2026-05-18T01:08:31.625485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:08:31.625485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9x8gTb+au8MYegHN/jgRjxjUxZIbNuqfYG40GTom/9hd0JUzORX8aI6Wpsr5n+hxVmIMbaMXKltTit6nVRiVBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:08:31.626065Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.05203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4941337797e68ed32bfcca67d81d3d89645363db3421905847ea93205f67f53","sha256:d8fa3f1c5a12ff6a1d24e3958b36d659d3eb74b5c54cf8101cd71d163338231d"],"state_sha256":"d677b53915ec392c899d28437d15e69099767cf778e4acdc104ceb3482fe35a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J0miQomrengZXFbXSwUy5z9vl2EwvUmXBu2kC3jcunLLriqcgGm8Xy07hV5JqC+UsjRjw5KjDEBha/aRKUMRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T21:48:40.433920Z","bundle_sha256":"b647b49d0d46d6309920025b6fc3c03691799bf892e213b74ab5c72d3a16dac5"}}