{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PFXZKQTW5FSWF7AQSXLU3VDLLQ","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":"2ed633bbeb39b6cbb490b1870e7eed0495c6942fdcdeabd63f44f1200e190425","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:33:36Z","title_canon_sha256":"7c488563a218408c3646f9e77a2fa75db6456c56f4697fe01a88955fa36c217f"},"schema_version":"1.0","source":{"id":"2505.23358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23358","created_at":"2026-07-05T11:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23358v1","created_at":"2026-07-05T11:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23358","created_at":"2026-07-05T11:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"PFXZKQTW5FSW","created_at":"2026-07-05T11:12:00Z"},{"alias_kind":"pith_short_16","alias_value":"PFXZKQTW5FSWF7AQ","created_at":"2026-07-05T11:12:00Z"},{"alias_kind":"pith_short_8","alias_value":"PFXZKQTW","created_at":"2026-07-05T11:12:00Z"}],"graph_snapshots":[{"event_id":"sha256:f764bb1a31acb143949c48d9b15bea8b87190d47a73f57f64caf53928c8d7cb9","target":"graph","created_at":"2026-07-05T11:12:00Z","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/2505.23358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Muzammil Behzad, Reem AlJunaid","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:33:36Z","title":"Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23358","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":"sha256:370dfd71a6a4f55a6b55cd66585ae863581e037b06fc634287dbf6b36fd3fc04","target":"record","created_at":"2026-07-05T11:12:00Z","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":"2ed633bbeb39b6cbb490b1870e7eed0495c6942fdcdeabd63f44f1200e190425","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T11:33:36Z","title_canon_sha256":"7c488563a218408c3646f9e77a2fa75db6456c56f4697fe01a88955fa36c217f"},"schema_version":"1.0","source":{"id":"2505.23358","kind":"arxiv","version":1}},"canonical_sha256":"796f954276e96562fc1095d74dd46b5c33b97b14e4fe512fa306a335f05642d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"796f954276e96562fc1095d74dd46b5c33b97b14e4fe512fa306a335f05642d3","first_computed_at":"2026-07-05T11:12:00.240469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:00.240469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NYLghe8oxZnJ2YXbJB96QgLlP28BrMz/6MIk2y9eFFY85yS3hlexMSNnqnQG5McdKgWF/lBKRfNtnuoNUHpQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:00.240966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:370dfd71a6a4f55a6b55cd66585ae863581e037b06fc634287dbf6b36fd3fc04","sha256:f764bb1a31acb143949c48d9b15bea8b87190d47a73f57f64caf53928c8d7cb9"],"state_sha256":"5dce01ba1430d5792915916a535ec03d102e212cbf11e29173890809cb16dd02"}