{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ORXZ6GFMKIBJ7JPH6JY4HUHOIK","short_pith_number":"pith:ORXZ6GFM","schema_version":"1.0","canonical_sha256":"746f9f18ac52029fa5e7f271c3d0ee42bce67af4262e3be4834842ab55ad575f","source":{"kind":"arxiv","id":"2309.04965","version":2},"attestation_state":"computed","paper":{"title":"Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Guisheng Liu, Haiyan Fu, Xiangyang Luo, Yanqing Guo, Yi Li, Zhengcong Fei","submitted_at":"2023-09-10T08:55:24Z","abstract_excerpt":"While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems. In this work, we propose a lightweight image captioning network in combination with continuous diffusion, called Prefix-diffusion. To achieve diversity, we design an efficient method that injects prefix image embeddings into the denoising process of the diffusion model. In order to reduce trainable parameters, we employ a pre-trained model to extract image features and further desig"},"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":"2309.04965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-10T08:55:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3bd7fe577a2edae90ea7ac14f4ac483b3bf83c07b82b34a0211d2c98057b3509","abstract_canon_sha256":"c9b6fdca5d91052ea7eeea79dbe9f90bd3befecb3025c03ec398ca2dfbcd6c47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:25.555872Z","signature_b64":"ZHrzttAZ84yu2FE+/eh2EmhwDYvb2TAw/Ez5ivdKY/C8uq2tmTkQWAvPpi45BBIQMQSQyaUPP+KCEdKgbEAnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"746f9f18ac52029fa5e7f271c3d0ee42bce67af4262e3be4834842ab55ad575f","last_reissued_at":"2026-07-05T07:01:25.555404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:25.555404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Guisheng Liu, Haiyan Fu, Xiangyang Luo, Yanqing Guo, Yi Li, Zhengcong Fei","submitted_at":"2023-09-10T08:55:24Z","abstract_excerpt":"While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems. In this work, we propose a lightweight image captioning network in combination with continuous diffusion, called Prefix-diffusion. To achieve diversity, we design an efficient method that injects prefix image embeddings into the denoising process of the diffusion model. In order to reduce trainable parameters, we employ a pre-trained model to extract image features and further desig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04965","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/2309.04965/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":"2309.04965","created_at":"2026-07-05T07:01:25.555464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04965v2","created_at":"2026-07-05T07:01:25.555464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04965","created_at":"2026-07-05T07:01:25.555464+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORXZ6GFMKIBJ","created_at":"2026-07-05T07:01:25.555464+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORXZ6GFMKIBJ7JPH","created_at":"2026-07-05T07:01:25.555464+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORXZ6GFM","created_at":"2026-07-05T07:01:25.555464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01115","citing_title":"DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK","json":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK.json","graph_json":"https://pith.science/api/pith-number/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/graph.json","events_json":"https://pith.science/api/pith-number/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/events.json","paper":"https://pith.science/paper/ORXZ6GFM"},"agent_actions":{"view_html":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK","download_json":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK.json","view_paper":"https://pith.science/paper/ORXZ6GFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04965&json=true","fetch_graph":"https://pith.science/api/pith-number/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/graph.json","fetch_events":"https://pith.science/api/pith-number/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/action/storage_attestation","attest_author":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/action/author_attestation","sign_citation":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/action/citation_signature","submit_replication":"https://pith.science/pith/ORXZ6GFMKIBJ7JPH6JY4HUHOIK/action/replication_record"}},"created_at":"2026-07-05T07:01:25.555464+00:00","updated_at":"2026-07-05T07:01:25.555464+00:00"}