{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W5MRKKOPNPTCOO7KGY5HP7FATC","short_pith_number":"pith:W5MRKKOP","schema_version":"1.0","canonical_sha256":"b7591529cf6be6273bea363a77fca098adcd09a11c155d804b358ae51685ae19","source":{"kind":"arxiv","id":"2312.05349","version":3},"attestation_state":"computed","paper":{"title":"PixLore: A Dataset-driven Approach to Rich Image Captioning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Antonio Jos\\'e Serrano-L\\'opez, Diego Bonilla-Salvador, Fernando Mateo, Joan Vila-Franc\\'es, Marcelino Mart\\'inez-Sober, Pablo Rodr\\'iguez-Belenguer","submitted_at":"2023-12-08T20:12:26Z","abstract_excerpt":"In the domain of vision-language integration, generating detailed image captions poses a significant challenge due to the lack of curated and rich datasets. This study introduces PixLore, a novel method that leverages Querying Transformers through the fine-tuning of the BLIP-2 model using the LoRa method on a standard commercial GPU. The followed approach, which involves training on a carefully assembled dataset from state-of-the-art Computer Vision models combined and augmented by ChatGPT, addresses the question of whether intricate image understanding can be achieved with an ensemble of smal"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.05349","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T20:12:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16dd6444062c350e73d67b718c0e59751b5b6b6a65b7f8be7f10ae8d00f68bf9","abstract_canon_sha256":"daea9ad8175d77a0254946ecc5bf4b665c4fdc91d9aed3beb5a88ba98c00eca3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:32.012695Z","signature_b64":"/zh6eQegr9nO1zkKs929447Ubn8QM2ehVnoLkBBYBtx6Cg8cYLJfJgnwLliXceDwm4AFqvVh1ww5iOtvvpstBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7591529cf6be6273bea363a77fca098adcd09a11c155d804b358ae51685ae19","last_reissued_at":"2026-07-05T09:24:32.012120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:32.012120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixLore: A Dataset-driven Approach to Rich Image Captioning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Antonio Jos\\'e Serrano-L\\'opez, Diego Bonilla-Salvador, Fernando Mateo, Joan Vila-Franc\\'es, Marcelino Mart\\'inez-Sober, Pablo Rodr\\'iguez-Belenguer","submitted_at":"2023-12-08T20:12:26Z","abstract_excerpt":"In the domain of vision-language integration, generating detailed image captions poses a significant challenge due to the lack of curated and rich datasets. This study introduces PixLore, a novel method that leverages Querying Transformers through the fine-tuning of the BLIP-2 model using the LoRa method on a standard commercial GPU. The followed approach, which involves training on a carefully assembled dataset from state-of-the-art Computer Vision models combined and augmented by ChatGPT, addresses the question of whether intricate image understanding can be achieved with an ensemble of smal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05349","kind":"arxiv","version":3},"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/2312.05349/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.05349","created_at":"2026-07-05T09:24:32.012196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05349v3","created_at":"2026-07-05T09:24:32.012196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05349","created_at":"2026-07-05T09:24:32.012196+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5MRKKOPNPTC","created_at":"2026-07-05T09:24:32.012196+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5MRKKOPNPTCOO7K","created_at":"2026-07-05T09:24:32.012196+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5MRKKOP","created_at":"2026-07-05T09:24:32.012196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05623","citing_title":"DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC","json":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC.json","graph_json":"https://pith.science/api/pith-number/W5MRKKOPNPTCOO7KGY5HP7FATC/graph.json","events_json":"https://pith.science/api/pith-number/W5MRKKOPNPTCOO7KGY5HP7FATC/events.json","paper":"https://pith.science/paper/W5MRKKOP"},"agent_actions":{"view_html":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC","download_json":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC.json","view_paper":"https://pith.science/paper/W5MRKKOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05349&json=true","fetch_graph":"https://pith.science/api/pith-number/W5MRKKOPNPTCOO7KGY5HP7FATC/graph.json","fetch_events":"https://pith.science/api/pith-number/W5MRKKOPNPTCOO7KGY5HP7FATC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC/action/storage_attestation","attest_author":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC/action/author_attestation","sign_citation":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC/action/citation_signature","submit_replication":"https://pith.science/pith/W5MRKKOPNPTCOO7KGY5HP7FATC/action/replication_record"}},"created_at":"2026-07-05T09:24:32.012196+00:00","updated_at":"2026-07-05T09:24:32.012196+00:00"}