{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HEP7P34ORYNIDFBDC3TGLOME3F","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":"b921e4d8534881a22f052940f89fb0067b98fd9122f30e664aff2e03d827e96a","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T03:27:57Z","title_canon_sha256":"67f10371c3a75ba001096f72473b4f95b8551a38976ab4871b5c9e1604e36950"},"schema_version":"1.0","source":{"id":"2607.28986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28986","created_at":"2026-08-03T01:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28986v1","created_at":"2026-08-03T01:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28986","created_at":"2026-08-03T01:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"HEP7P34ORYNI","created_at":"2026-08-03T01:17:52Z"},{"alias_kind":"pith_short_16","alias_value":"HEP7P34ORYNIDFBD","created_at":"2026-08-03T01:17:52Z"},{"alias_kind":"pith_short_8","alias_value":"HEP7P34O","created_at":"2026-08-03T01:17:52Z"}],"graph_snapshots":[{"event_id":"sha256:413639b30f6f20f75d09b771c20cfa6fc3255eed2994f449f5926046f64dc317","target":"graph","created_at":"2026-08-03T01:17:52Z","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/2607.28986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers. Existing retrieval-augmented methods score image-text alignment once, at retrieval, then commit the captioner's autoregressive beam under language-model probability alone, leaving the decoder without further visual grounding feedback. Progress has stalled, with no method improving on the strict-regime best since 2024.\n  We propose Adjudicated Captioning, an inference-time multi-agent framework that restores ","authors_text":"Duy Tran Thanh, Long Nguyen-Vu, Ngo Tan Vu Khanh, Thien-Phuc Doan","cross_cats":["cs.AI","cs.CL","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T03:27:57Z","title":"Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28986","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":"sha256:20e137e37b9565a03ae5e02638b7715b1782036caa6e5e9ea1e644133c243115","target":"record","created_at":"2026-08-03T01:17:52Z","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":"b921e4d8534881a22f052940f89fb0067b98fd9122f30e664aff2e03d827e96a","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T03:27:57Z","title_canon_sha256":"67f10371c3a75ba001096f72473b4f95b8551a38976ab4871b5c9e1604e36950"},"schema_version":"1.0","source":{"id":"2607.28986","kind":"arxiv","version":1}},"canonical_sha256":"391ff7ef8e8e1a81942316e665b984d96f0eec601235ff02d03dc4c5f2d38446","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"391ff7ef8e8e1a81942316e665b984d96f0eec601235ff02d03dc4c5f2d38446","first_computed_at":"2026-08-03T01:17:52.006072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:17:52.006072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2CeSqi/i2fPVHP9DFmprkaS7DDDJZywKC0KZMlW6lMzvLNqHaVydfPRqd7+6XDn10pS9s3HWM72A9Klkce/BDw==","signature_status":"signed_v1","signed_at":"2026-08-03T01:17:52.007563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20e137e37b9565a03ae5e02638b7715b1782036caa6e5e9ea1e644133c243115","sha256:413639b30f6f20f75d09b771c20cfa6fc3255eed2994f449f5926046f64dc317"],"state_sha256":"488a311dce817db2a55b84d8a64b5bbec2781ccc0612906e87cc9bc23a1a2769"}