{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PFXZKQTW5FSWF7AQSXLU3VDLLQ","short_pith_number":"pith:PFXZKQTW","schema_version":"1.0","canonical_sha256":"796f954276e96562fc1095d74dd46b5c33b97b14e4fe512fa306a335f05642d3","source":{"kind":"arxiv","id":"2505.23358","version":1},"attestation_state":"computed","paper":{"title":"Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Muzammil Behzad, Reem AlJunaid","submitted_at":"2025-05-29T11:33:36Z","abstract_excerpt":"Generating informative and knowledge-rich image captions remains a challenge for many existing captioning models, which often produce generic descriptions that lack specificity and contextual depth. To address this limitation, we propose KRCapVLM, a knowledge replay-based novel image captioning framework using vision-language model. We incorporate beam search decoding to generate more diverse and coherent captions. We also integrate attention-based modules into the image encoder to enhance feature representation. Finally, we employ training schedulers to improve stability and ensure smoother c"},"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":"2505.23358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:33:36Z","cross_cats_sorted":[],"title_canon_sha256":"7c488563a218408c3646f9e77a2fa75db6456c56f4697fe01a88955fa36c217f","abstract_canon_sha256":"2ed633bbeb39b6cbb490b1870e7eed0495c6942fdcdeabd63f44f1200e190425"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:00.240966Z","signature_b64":"NYLghe8oxZnJ2YXbJB96QgLlP28BrMz/6MIk2y9eFFY85yS3hlexMSNnqnQG5McdKgWF/lBKRfNtnuoNUHpQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796f954276e96562fc1095d74dd46b5c33b97b14e4fe512fa306a335f05642d3","last_reissued_at":"2026-07-05T11:12:00.240469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:00.240469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Muzammil Behzad, Reem AlJunaid","submitted_at":"2025-05-29T11:33:36Z","abstract_excerpt":"Generating informative and knowledge-rich image captions remains a challenge for many existing captioning models, which often produce generic descriptions that lack specificity and contextual depth. To address this limitation, we propose KRCapVLM, a knowledge replay-based novel image captioning framework using vision-language model. We incorporate beam search decoding to generate more diverse and coherent captions. We also integrate attention-based modules into the image encoder to enhance feature representation. Finally, we employ training schedulers to improve stability and ensure smoother c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23358","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/2505.23358/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":"2505.23358","created_at":"2026-07-05T11:12:00.240528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23358v1","created_at":"2026-07-05T11:12:00.240528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23358","created_at":"2026-07-05T11:12:00.240528+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFXZKQTW5FSW","created_at":"2026-07-05T11:12:00.240528+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFXZKQTW5FSWF7AQ","created_at":"2026-07-05T11:12:00.240528+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFXZKQTW","created_at":"2026-07-05T11:12:00.240528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ","json":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ.json","graph_json":"https://pith.science/api/pith-number/PFXZKQTW5FSWF7AQSXLU3VDLLQ/graph.json","events_json":"https://pith.science/api/pith-number/PFXZKQTW5FSWF7AQSXLU3VDLLQ/events.json","paper":"https://pith.science/paper/PFXZKQTW"},"agent_actions":{"view_html":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ","download_json":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ.json","view_paper":"https://pith.science/paper/PFXZKQTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23358&json=true","fetch_graph":"https://pith.science/api/pith-number/PFXZKQTW5FSWF7AQSXLU3VDLLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PFXZKQTW5FSWF7AQSXLU3VDLLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ/action/storage_attestation","attest_author":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ/action/author_attestation","sign_citation":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ/action/citation_signature","submit_replication":"https://pith.science/pith/PFXZKQTW5FSWF7AQSXLU3VDLLQ/action/replication_record"}},"created_at":"2026-07-05T11:12:00.240528+00:00","updated_at":"2026-07-05T11:12:00.240528+00:00"}