{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NKF3BXRTGUANCHEMDRWCTECYU3","short_pith_number":"pith:NKF3BXRT","schema_version":"1.0","canonical_sha256":"6a8bb0de333500d11c8c1c6c299058a6db9cdcc605b2960915a61765ed3f38bf","source":{"kind":"arxiv","id":"2606.29997","version":1},"attestation_state":"computed","paper":{"title":"Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Yashima, Kazuki Matsuda, Komei Sugiura, Shinnosuke Hirano, Shuitsu Koyama, Yuiga Wada","submitted_at":"2026-06-29T09:07:29Z","abstract_excerpt":"Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limited alignment with human judgments. Recent approaches using large language models (LLMs), commonly referred to as LLM-as-a-Judge, have improved alignment with human judgments but still suffer from a mismatch between large-vocabulary language modeling and evaluation over a small label set. To address this, we propose Rigel, an automatic evaluation metric for image and video captioning, based on self-distilled score adaptation. The metric employs an e"},"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":"2606.29997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T09:07:29Z","cross_cats_sorted":[],"title_canon_sha256":"2f9d476288000d35c14daa075cb4ba84cf54b103e2fa3b4e8a367cca91e9258f","abstract_canon_sha256":"735dcdbe0678db9849b9a9567465e2ffa41bd97f3cc3d4a5dc02ad1d25cb853c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:44.921621Z","signature_b64":"XEq1piGL5BtMOjWhxfwNi8oRA5EklCCo2e34tJ4oYwYSLFmbEuvc4MMh8OZxKjnNmvvXzKze8f9MB+4CHSe5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a8bb0de333500d11c8c1c6c299058a6db9cdcc605b2960915a61765ed3f38bf","last_reissued_at":"2026-06-30T02:17:44.920549Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:44.920549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Yashima, Kazuki Matsuda, Komei Sugiura, Shinnosuke Hirano, Shuitsu Koyama, Yuiga Wada","submitted_at":"2026-06-29T09:07:29Z","abstract_excerpt":"Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limited alignment with human judgments. Recent approaches using large language models (LLMs), commonly referred to as LLM-as-a-Judge, have improved alignment with human judgments but still suffer from a mismatch between large-vocabulary language modeling and evaluation over a small label set. To address this, we propose Rigel, an automatic evaluation metric for image and video captioning, based on self-distilled score adaptation. The metric employs an e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29997","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/2606.29997/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":"2606.29997","created_at":"2026-06-30T02:17:44.920680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29997v1","created_at":"2026-06-30T02:17:44.920680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29997","created_at":"2026-06-30T02:17:44.920680+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKF3BXRTGUAN","created_at":"2026-06-30T02:17:44.920680+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKF3BXRTGUANCHEM","created_at":"2026-06-30T02:17:44.920680+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKF3BXRT","created_at":"2026-06-30T02:17:44.920680+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/NKF3BXRTGUANCHEMDRWCTECYU3","json":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3.json","graph_json":"https://pith.science/api/pith-number/NKF3BXRTGUANCHEMDRWCTECYU3/graph.json","events_json":"https://pith.science/api/pith-number/NKF3BXRTGUANCHEMDRWCTECYU3/events.json","paper":"https://pith.science/paper/NKF3BXRT"},"agent_actions":{"view_html":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3","download_json":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3.json","view_paper":"https://pith.science/paper/NKF3BXRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29997&json=true","fetch_graph":"https://pith.science/api/pith-number/NKF3BXRTGUANCHEMDRWCTECYU3/graph.json","fetch_events":"https://pith.science/api/pith-number/NKF3BXRTGUANCHEMDRWCTECYU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3/action/storage_attestation","attest_author":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3/action/author_attestation","sign_citation":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3/action/citation_signature","submit_replication":"https://pith.science/pith/NKF3BXRTGUANCHEMDRWCTECYU3/action/replication_record"}},"created_at":"2026-06-30T02:17:44.920680+00:00","updated_at":"2026-06-30T02:17:44.920680+00:00"}