{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T6IFQ5ITQPELIEFWS7PC7YUVUT","short_pith_number":"pith:T6IFQ5IT","canonical_record":{"source":{"id":"2305.17718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T13:16:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9983e45c0dd85f9814eca6a00dfc6ee684940d602ef3713ce30e3e8e4004a0e3","abstract_canon_sha256":"ea18fc609f82b06fa025c2e750c9b10038a698e3c46a49f0d5f0012328c4621c"},"schema_version":"1.0"},"canonical_sha256":"9f9058751383c8b410b697de2fe295a4ea0cbf757912c667d072225ac899bbe5","source":{"kind":"arxiv","id":"2305.17718","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17718","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17718v2","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17718","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"T6IFQ5ITQPEL","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"T6IFQ5ITQPELIEFW","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"T6IFQ5IT","created_at":"2026-07-05T07:13:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T6IFQ5ITQPELIEFWS7PC7YUVUT","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T13:16:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9983e45c0dd85f9814eca6a00dfc6ee684940d602ef3713ce30e3e8e4004a0e3","abstract_canon_sha256":"ea18fc609f82b06fa025c2e750c9b10038a698e3c46a49f0d5f0012328c4621c"},"schema_version":"1.0"},"canonical_sha256":"9f9058751383c8b410b697de2fe295a4ea0cbf757912c667d072225ac899bbe5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:10.903186Z","signature_b64":"BXw8+Pq8fZQGi+UAQrSasU9fELOowbcUog+wn4oVTptCbGl9GLvX54n/lEr6yBOT1lrYha+gHF7/92KynNn6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f9058751383c8b410b697de2fe295a4ea0cbf757912c667d072225ac899bbe5","last_reissued_at":"2026-07-05T07:13:10.902615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:10.902615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17718","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KA0lw85Rn2IqqsHYlgr1dIrOzsHKAHXEEX38pK8/VI/N9mNfiEAaEZ/5pvueLkTW7/FpURHe8dVu4kqCD9FNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:40:01.099687Z"},"content_sha256":"e81c023642c3e6ac338962e9a62f95daf9b08c32c33e9b0c200eb11889881e3b","schema_version":"1.0","event_id":"sha256:e81c023642c3e6ac338962e9a62f95daf9b08c32c33e9b0c200eb11889881e3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T6IFQ5ITQPELIEFWS7PC7YUVUT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"David Bensaid, Noam Rotstein, Ron Kimmel, Roy Ganz, Shaked Brody","submitted_at":"2023-05-28T13:16:03Z","abstract_excerpt":"The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image details. This limitation can be traced back to the image-text datasets; while their captions typically offer a general description of image content, they frequently omit salient details. Considering the magnitude of these datasets, manual reannotation is impractical, emphasizing the need for an automated approach. To address this challenge, we leverage existing c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17718","kind":"arxiv","version":2},"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/2305.17718/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":"2026-07-05T07:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e+8KcE08Id7lKuKSAtQu2KP9xTdxkRmhzbcVKjfSGsMZVSsfokV+1VZ2+fpe3mYDUpAxa0DOypgUZw9/ectIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:40:01.100195Z"},"content_sha256":"a33dd24974cc2020bf3cb340287dfe82d2133d69e2b3687b88b1399df5d414dd","schema_version":"1.0","event_id":"sha256:a33dd24974cc2020bf3cb340287dfe82d2133d69e2b3687b88b1399df5d414dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6IFQ5ITQPELIEFWS7PC7YUVUT/bundle.json","state_url":"https://pith.science/pith/T6IFQ5ITQPELIEFWS7PC7YUVUT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6IFQ5ITQPELIEFWS7PC7YUVUT/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":"2026-08-08T22:40:01Z","links":{"resolver":"https://pith.science/pith/T6IFQ5ITQPELIEFWS7PC7YUVUT","bundle":"https://pith.science/pith/T6IFQ5ITQPELIEFWS7PC7YUVUT/bundle.json","state":"https://pith.science/pith/T6IFQ5ITQPELIEFWS7PC7YUVUT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6IFQ5ITQPELIEFWS7PC7YUVUT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T6IFQ5ITQPELIEFWS7PC7YUVUT","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":"ea18fc609f82b06fa025c2e750c9b10038a698e3c46a49f0d5f0012328c4621c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T13:16:03Z","title_canon_sha256":"9983e45c0dd85f9814eca6a00dfc6ee684940d602ef3713ce30e3e8e4004a0e3"},"schema_version":"1.0","source":{"id":"2305.17718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17718","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17718v2","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17718","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"T6IFQ5ITQPEL","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"T6IFQ5ITQPELIEFW","created_at":"2026-07-05T07:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"T6IFQ5IT","created_at":"2026-07-05T07:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:a33dd24974cc2020bf3cb340287dfe82d2133d69e2b3687b88b1399df5d414dd","target":"graph","created_at":"2026-07-05T07:13:10Z","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/2305.17718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image details. This limitation can be traced back to the image-text datasets; while their captions typically offer a general description of image content, they frequently omit salient details. Considering the magnitude of these datasets, manual reannotation is impractical, emphasizing the need for an automated approach. To address this challenge, we leverage existing c","authors_text":"David Bensaid, Noam Rotstein, Ron Kimmel, Roy Ganz, Shaked Brody","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T13:16:03Z","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17718","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:e81c023642c3e6ac338962e9a62f95daf9b08c32c33e9b0c200eb11889881e3b","target":"record","created_at":"2026-07-05T07:13:10Z","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":"ea18fc609f82b06fa025c2e750c9b10038a698e3c46a49f0d5f0012328c4621c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-28T13:16:03Z","title_canon_sha256":"9983e45c0dd85f9814eca6a00dfc6ee684940d602ef3713ce30e3e8e4004a0e3"},"schema_version":"1.0","source":{"id":"2305.17718","kind":"arxiv","version":2}},"canonical_sha256":"9f9058751383c8b410b697de2fe295a4ea0cbf757912c667d072225ac899bbe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f9058751383c8b410b697de2fe295a4ea0cbf757912c667d072225ac899bbe5","first_computed_at":"2026-07-05T07:13:10.902615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:10.902615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BXw8+Pq8fZQGi+UAQrSasU9fELOowbcUog+wn4oVTptCbGl9GLvX54n/lEr6yBOT1lrYha+gHF7/92KynNn6Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:10.903186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e81c023642c3e6ac338962e9a62f95daf9b08c32c33e9b0c200eb11889881e3b","sha256:a33dd24974cc2020bf3cb340287dfe82d2133d69e2b3687b88b1399df5d414dd"],"state_sha256":"54aa8db02256efad0f0994e8fa23571001a4be009a866709ecea886477928eb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdiZkCge6g6bXZnmnRNgpL8v1o/f4O75kCVHOlXt8g4+2aJlnIw9CT5m5tXdUjPcIsbYoJXtu+y9YknZ5RLpDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:40:01.105689Z","bundle_sha256":"e3c90aa41a390622e35db3cee50164d20e09982ce42a8a75b5b63af4fb7ba76b"}}