{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EVSGCPEQZTQJJ7MP7XKAD57LTC","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":"a49e692e57ca2208364a83cba10f517b6f8b7ee938bf0200907186c2afe0ed32","cross_cats_sorted":["cs.AI","cs.CL","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:31:51Z","title_canon_sha256":"8786f21197971bf2acff173069b7d8519ba239f18b8c0e26728cfdf72765987d"},"schema_version":"1.0","source":{"id":"2308.03767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.03767","created_at":"2026-07-05T06:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2308.03767v1","created_at":"2026-07-05T06:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03767","created_at":"2026-07-05T06:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"EVSGCPEQZTQJ","created_at":"2026-07-05T06:39:07Z"},{"alias_kind":"pith_short_16","alias_value":"EVSGCPEQZTQJJ7MP","created_at":"2026-07-05T06:39:07Z"},{"alias_kind":"pith_short_8","alias_value":"EVSGCPEQ","created_at":"2026-07-05T06:39:07Z"}],"graph_snapshots":[{"event_id":"sha256:51c1a0986fb20d5589ccc84504031e7ed2aae4e14bbca5748f1592abba39403b","target":"graph","created_at":"2026-07-05T06:39:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.03767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Captioning images is a challenging scene-understanding task that connects computer vision and natural language processing. While image captioning models have been successful in producing excellent descriptions, the field has primarily focused on generating a single sentence for 2D images. This paper investigates whether integrating depth information with RGB images can enhance the captioning task and generate better descriptions. For this purpose, we propose a Transformer-based encoder-decoder framework for generating a multi-sentence description of a 3D scene. The RGB image and its correspond","authors_text":"Aya Mahmoud Ahmed, Khaled F. Hussain, Mohamed Yousef, Yousef Bassyouni Mahdy","cross_cats":["cs.AI","cs.CL","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:31:51Z","title":"Enhancing image captioning with depth information using a Transformer-based framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03767","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":"sha256:9877e530740b94e5842f9896c7009d021f253f74aa3e5781bf6e74050f0bcef7","target":"record","created_at":"2026-07-05T06:39:07Z","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":"a49e692e57ca2208364a83cba10f517b6f8b7ee938bf0200907186c2afe0ed32","cross_cats_sorted":["cs.AI","cs.CL","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:31:51Z","title_canon_sha256":"8786f21197971bf2acff173069b7d8519ba239f18b8c0e26728cfdf72765987d"},"schema_version":"1.0","source":{"id":"2308.03767","kind":"arxiv","version":1}},"canonical_sha256":"2564613c90cce094fd8ffdd401f7eb98ab77736814af924d286fba2f8b10e00d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2564613c90cce094fd8ffdd401f7eb98ab77736814af924d286fba2f8b10e00d","first_computed_at":"2026-07-05T06:39:07.859609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:07.859609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ym5eQlUFwo3GAkloy4EScxtUrNKkuzlmhoBnl8EWvr/px4kh52MUjSWlNE1Av0NI5FKLQG7uSynfyhRwHlAKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:07.859966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.03767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9877e530740b94e5842f9896c7009d021f253f74aa3e5781bf6e74050f0bcef7","sha256:51c1a0986fb20d5589ccc84504031e7ed2aae4e14bbca5748f1592abba39403b"],"state_sha256":"ed705c9020625e30fb13d55618b1adda357e9ad4ad42c9123f851199156051f8"}