{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EVSGCPEQZTQJJ7MP7XKAD57LTC","short_pith_number":"pith:EVSGCPEQ","canonical_record":{"source":{"id":"2308.03767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:31:51Z","cross_cats_sorted":["cs.AI","cs.CL","eess.IV"],"title_canon_sha256":"8786f21197971bf2acff173069b7d8519ba239f18b8c0e26728cfdf72765987d","abstract_canon_sha256":"a49e692e57ca2208364a83cba10f517b6f8b7ee938bf0200907186c2afe0ed32"},"schema_version":"1.0"},"canonical_sha256":"2564613c90cce094fd8ffdd401f7eb98ab77736814af924d286fba2f8b10e00d","source":{"kind":"arxiv","id":"2308.03767","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EVSGCPEQZTQJJ7MP7XKAD57LTC","target":"record","payload":{"canonical_record":{"source":{"id":"2308.03767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:31:51Z","cross_cats_sorted":["cs.AI","cs.CL","eess.IV"],"title_canon_sha256":"8786f21197971bf2acff173069b7d8519ba239f18b8c0e26728cfdf72765987d","abstract_canon_sha256":"a49e692e57ca2208364a83cba10f517b6f8b7ee938bf0200907186c2afe0ed32"},"schema_version":"1.0"},"canonical_sha256":"2564613c90cce094fd8ffdd401f7eb98ab77736814af924d286fba2f8b10e00d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:07.859966Z","signature_b64":"ym5eQlUFwo3GAkloy4EScxtUrNKkuzlmhoBnl8EWvr/px4kh52MUjSWlNE1Av0NI5FKLQG7uSynfyhRwHlAKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2564613c90cce094fd8ffdd401f7eb98ab77736814af924d286fba2f8b10e00d","last_reissued_at":"2026-07-05T06:39:07.859609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:07.859609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.03767","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":"2026-07-05T06:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OWh0Z7bw6WUyva/xqivo2MfyXKB0x1sNgUxLQYxH47imBCSFrJSEl0+Esu7mPlpfkrEIZDQ9qzQ21wZY5HpqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:09:46.026143Z"},"content_sha256":"9877e530740b94e5842f9896c7009d021f253f74aa3e5781bf6e74050f0bcef7","schema_version":"1.0","event_id":"sha256:9877e530740b94e5842f9896c7009d021f253f74aa3e5781bf6e74050f0bcef7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EVSGCPEQZTQJJ7MP7XKAD57LTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing image captioning with depth information using a Transformer-based framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aya Mahmoud Ahmed, Khaled F. Hussain, Mohamed Yousef, Yousef Bassyouni Mahdy","submitted_at":"2023-07-24T17:31:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03767","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/2308.03767/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":"2026-07-05T06:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mpoX7ZvbHDRyjcuez8zBxaXhT3aqFp9Id+GUf5uEC6lt40gC0d26KmffGLBI81hg0brlUl9AbeSSTlHxEuVCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:09:46.026963Z"},"content_sha256":"51c1a0986fb20d5589ccc84504031e7ed2aae4e14bbca5748f1592abba39403b","schema_version":"1.0","event_id":"sha256:51c1a0986fb20d5589ccc84504031e7ed2aae4e14bbca5748f1592abba39403b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/bundle.json","state_url":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/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":"2026-08-14T09:09:46Z","links":{"resolver":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC","bundle":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/bundle.json","state":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JaNfUNUhSfppYZNN8FEp8eVtclXYgL6OeYE6TM8p//F3rEZV1LJNGu63kFSNiUd30hHugSfdHqwb5Jh24s3NCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:09:46.034773Z","bundle_sha256":"27c4b07a4b91ddde2de4fb4c156d8cf9dbe3298742819edb45f02c7242b34e95"}}