{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZBIOM7TKGWDGFNJV35TUE7G7QX","short_pith_number":"pith:ZBIOM7TK","canonical_record":{"source":{"id":"2105.08106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-17T18:35:24Z","cross_cats_sorted":[],"title_canon_sha256":"51072978ff36f82a01ddeaff7f373a614d3f1e3c00546676f99fb382f849413e","abstract_canon_sha256":"f5de75f11b5779970c5fbd6f5f3080f3950c30b9ae6a74db306b6d53ab93ee03"},"schema_version":"1.0"},"canonical_sha256":"c850e67e6a358662b535df67427cdf85c3370ee16dc0863e53d80ca5e0fe97ec","source":{"kind":"arxiv","id":"2105.08106","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08106","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08106v1","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08106","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZBIOM7TKGWDG","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZBIOM7TKGWDGFNJV","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZBIOM7TK","created_at":"2026-07-05T02:40:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZBIOM7TKGWDGFNJV35TUE7G7QX","target":"record","payload":{"canonical_record":{"source":{"id":"2105.08106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-17T18:35:24Z","cross_cats_sorted":[],"title_canon_sha256":"51072978ff36f82a01ddeaff7f373a614d3f1e3c00546676f99fb382f849413e","abstract_canon_sha256":"f5de75f11b5779970c5fbd6f5f3080f3950c30b9ae6a74db306b6d53ab93ee03"},"schema_version":"1.0"},"canonical_sha256":"c850e67e6a358662b535df67427cdf85c3370ee16dc0863e53d80ca5e0fe97ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:51.652444Z","signature_b64":"V8IDdesHpJ1Imjbv8yWyf/krgqB5Y/oeLAVrpvbPiK7uBTfHOxQ+XU0y6YwYJm1K6czRl2/Q5ZAGEPVNqt4gAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c850e67e6a358662b535df67427cdf85c3370ee16dc0863e53d80ca5e0fe97ec","last_reissued_at":"2026-07-05T02:40:51.651904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:51.651904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.08106","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":"2026-07-05T02:40:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cp9pALi7g2jURetrGJwbbCylid55Z6dKtXc2ovD+T7sWAoYC7xwa6gacIpAOfhpi5Zdx755jvMJXFiUcsmiVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:44:19.506314Z"},"content_sha256":"cee0f28e5b2ea4e3be818fe70f71fd7e151812fd54963b135c4090d90dbca85e","schema_version":"1.0","event_id":"sha256:cee0f28e5b2ea4e3be818fe70f71fd7e151812fd54963b135c4090d90dbca85e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZBIOM7TKGWDGFNJV35TUE7G7QX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Modal Image Captioning for the Visually Impaired","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daivat Bhatt, Hiba Ahsan, Kaivankumar Shah, Nikita Bhalla","submitted_at":"2021-05-17T18:35:24Z","abstract_excerpt":"One of the ways blind people understand their surroundings is by clicking images and relying on descriptions generated by image captioning systems. Current work on captioning images for the visually impaired do not use the textual data present in the image when generating captions. This problem is critical as many visual scenes contain text. Moreover, up to 21% of the questions asked by blind people about the images they click pertain to the text present in them. In this work, we propose altering AoANet, a state-of-the-art image captioning model, to leverage the text detected in the image as a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08106","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.08106/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:40:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GzR4Aq8a/XVsUqNypdkdQWEz75AZt6AUVWD9TkSTjce+XsN0b0oZdOtDuOrcOptmOpKw/UoEu2yiqwmmzh7QCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:44:19.507210Z"},"content_sha256":"6bdc6d1063ce8b1ae684a0952362bb11ba34cafbf1913f3c40f4a6425dbcc0dc","schema_version":"1.0","event_id":"sha256:6bdc6d1063ce8b1ae684a0952362bb11ba34cafbf1913f3c40f4a6425dbcc0dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBIOM7TKGWDGFNJV35TUE7G7QX/bundle.json","state_url":"https://pith.science/pith/ZBIOM7TKGWDGFNJV35TUE7G7QX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBIOM7TKGWDGFNJV35TUE7G7QX/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":"2026-08-09T00:44:19Z","links":{"resolver":"https://pith.science/pith/ZBIOM7TKGWDGFNJV35TUE7G7QX","bundle":"https://pith.science/pith/ZBIOM7TKGWDGFNJV35TUE7G7QX/bundle.json","state":"https://pith.science/pith/ZBIOM7TKGWDGFNJV35TUE7G7QX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBIOM7TKGWDGFNJV35TUE7G7QX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZBIOM7TKGWDGFNJV35TUE7G7QX","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":"f5de75f11b5779970c5fbd6f5f3080f3950c30b9ae6a74db306b6d53ab93ee03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-17T18:35:24Z","title_canon_sha256":"51072978ff36f82a01ddeaff7f373a614d3f1e3c00546676f99fb382f849413e"},"schema_version":"1.0","source":{"id":"2105.08106","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08106","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08106v1","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08106","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZBIOM7TKGWDG","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZBIOM7TKGWDGFNJV","created_at":"2026-07-05T02:40:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZBIOM7TK","created_at":"2026-07-05T02:40:51Z"}],"graph_snapshots":[{"event_id":"sha256:6bdc6d1063ce8b1ae684a0952362bb11ba34cafbf1913f3c40f4a6425dbcc0dc","target":"graph","created_at":"2026-07-05T02:40:51Z","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/2105.08106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the ways blind people understand their surroundings is by clicking images and relying on descriptions generated by image captioning systems. Current work on captioning images for the visually impaired do not use the textual data present in the image when generating captions. This problem is critical as many visual scenes contain text. Moreover, up to 21% of the questions asked by blind people about the images they click pertain to the text present in them. In this work, we propose altering AoANet, a state-of-the-art image captioning model, to leverage the text detected in the image as a","authors_text":"Daivat Bhatt, Hiba Ahsan, Kaivankumar Shah, Nikita Bhalla","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-17T18:35:24Z","title":"Multi-Modal Image Captioning for the Visually Impaired"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08106","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:cee0f28e5b2ea4e3be818fe70f71fd7e151812fd54963b135c4090d90dbca85e","target":"record","created_at":"2026-07-05T02:40:51Z","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":"f5de75f11b5779970c5fbd6f5f3080f3950c30b9ae6a74db306b6d53ab93ee03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-17T18:35:24Z","title_canon_sha256":"51072978ff36f82a01ddeaff7f373a614d3f1e3c00546676f99fb382f849413e"},"schema_version":"1.0","source":{"id":"2105.08106","kind":"arxiv","version":1}},"canonical_sha256":"c850e67e6a358662b535df67427cdf85c3370ee16dc0863e53d80ca5e0fe97ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c850e67e6a358662b535df67427cdf85c3370ee16dc0863e53d80ca5e0fe97ec","first_computed_at":"2026-07-05T02:40:51.651904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:51.651904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8IDdesHpJ1Imjbv8yWyf/krgqB5Y/oeLAVrpvbPiK7uBTfHOxQ+XU0y6YwYJm1K6czRl2/Q5ZAGEPVNqt4gAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:51.652444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.08106","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cee0f28e5b2ea4e3be818fe70f71fd7e151812fd54963b135c4090d90dbca85e","sha256:6bdc6d1063ce8b1ae684a0952362bb11ba34cafbf1913f3c40f4a6425dbcc0dc"],"state_sha256":"1b4483bc0efbb6d42a94f4cbab3772807ea1a4d935457ba193ac103c8d073e03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JsQhfnSQ5QUweGlBOo7veoEh7sFytnNaIxGciG06THC+tq5kBy0JneIqwbimPvQDxd0SLsIi+pclZjHnRGnUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:44:19.514275Z","bundle_sha256":"158ab7dcd0d1cfac3a317a42073a934fea48b5272222ed84fd26d331147d1d2b"}}