{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HEP7P34ORYNIDFBDC3TGLOME3F","short_pith_number":"pith:HEP7P34O","schema_version":"1.0","canonical_sha256":"391ff7ef8e8e1a81942316e665b984d96f0eec601235ff02d03dc4c5f2d38446","source":{"kind":"arxiv","id":"2607.28986","version":1},"attestation_state":"computed","paper":{"title":"Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.CV","authors_text":"Duy Tran Thanh, Long Nguyen-Vu, Ngo Tan Vu Khanh, Thien-Phuc Doan","submitted_at":"2026-07-31T03:27:57Z","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 "},"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":"2607.28986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T03:27:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"title_canon_sha256":"67f10371c3a75ba001096f72473b4f95b8551a38976ab4871b5c9e1604e36950","abstract_canon_sha256":"b921e4d8534881a22f052940f89fb0067b98fd9122f30e664aff2e03d827e96a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:17:52.007563Z","signature_b64":"2CeSqi/i2fPVHP9DFmprkaS7DDDJZywKC0KZMlW6lMzvLNqHaVydfPRqd7+6XDn10pS9s3HWM72A9Klkce/BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"391ff7ef8e8e1a81942316e665b984d96f0eec601235ff02d03dc4c5f2d38446","last_reissued_at":"2026-08-03T01:17:52.006072Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:17:52.006072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.CV","authors_text":"Duy Tran Thanh, Long Nguyen-Vu, Ngo Tan Vu Khanh, Thien-Phuc Doan","submitted_at":"2026-07-31T03:27:57Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28986","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/2607.28986/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":"2607.28986","created_at":"2026-08-03T01:17:52.006969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28986v1","created_at":"2026-08-03T01:17:52.006969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28986","created_at":"2026-08-03T01:17:52.006969+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEP7P34ORYNI","created_at":"2026-08-03T01:17:52.006969+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEP7P34ORYNIDFBD","created_at":"2026-08-03T01:17:52.006969+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEP7P34O","created_at":"2026-08-03T01:17:52.006969+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/HEP7P34ORYNIDFBDC3TGLOME3F","json":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F.json","graph_json":"https://pith.science/api/pith-number/HEP7P34ORYNIDFBDC3TGLOME3F/graph.json","events_json":"https://pith.science/api/pith-number/HEP7P34ORYNIDFBDC3TGLOME3F/events.json","paper":"https://pith.science/paper/HEP7P34O"},"agent_actions":{"view_html":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F","download_json":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F.json","view_paper":"https://pith.science/paper/HEP7P34O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28986&json=true","fetch_graph":"https://pith.science/api/pith-number/HEP7P34ORYNIDFBDC3TGLOME3F/graph.json","fetch_events":"https://pith.science/api/pith-number/HEP7P34ORYNIDFBDC3TGLOME3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F/action/storage_attestation","attest_author":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F/action/author_attestation","sign_citation":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F/action/citation_signature","submit_replication":"https://pith.science/pith/HEP7P34ORYNIDFBDC3TGLOME3F/action/replication_record"}},"created_at":"2026-08-03T01:17:52.006969+00:00","updated_at":"2026-08-03T01:17:52.006969+00:00"}