{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WKZXOXQU2Z7Z5TMNDYBKFLCMXK","short_pith_number":"pith:WKZXOXQU","schema_version":"1.0","canonical_sha256":"b2b3775e14d67f9ecd8d1e02a2ac4cba806d3c69eb4729c1a5d062e520b40a67","source":{"kind":"arxiv","id":"2605.21728","version":1},"attestation_state":"computed","paper":{"title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bruno Martins, Chrysoula Zerva, Gon\\c{c}alo Gomes","submitted_at":"2026-05-20T20:43:38Z","abstract_excerpt":"Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve extensive computational costs associated with the use of Large Language Models (LLMs) as judges, or instead suffer from the limitations of standard CLIP-based encoders, such as strict token limits, lack of fine-grained sensitivity, or lack of compositional generalization by treating captions as ``bags-of-words.'' We propose a new learned metric that tackles the a"},"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":"2605.21728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T20:43:38Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9c927717ab25f79663b9da931b2461c3f44248d83b62a9d519c5517a17ab3a9d","abstract_canon_sha256":"cbf535b068a3684bdf02ec7958e0e9b175c7e1fa6bcdba19f024b52b4f89cd11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:29.630995Z","signature_b64":"CftgsoHtRzt1jnqGja1TxWwrFSPssMtRZcXnhvlL0oMLbmTi5ky6cQnG6NH3wEeLgth4u+WQmzMMYyDbXda9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b3775e14d67f9ecd8d1e02a2ac4cba806d3c69eb4729c1a5d062e520b40a67","last_reissued_at":"2026-05-22T01:03:29.630334Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:29.630334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bruno Martins, Chrysoula Zerva, Gon\\c{c}alo Gomes","submitted_at":"2026-05-20T20:43:38Z","abstract_excerpt":"Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve extensive computational costs associated with the use of Large Language Models (LLMs) as judges, or instead suffer from the limitations of standard CLIP-based encoders, such as strict token limits, lack of fine-grained sensitivity, or lack of compositional generalization by treating captions as ``bags-of-words.'' We propose a new learned metric that tackles the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21728","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/2605.21728/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":"2605.21728","created_at":"2026-05-22T01:03:29.630440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21728v1","created_at":"2026-05-22T01:03:29.630440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21728","created_at":"2026-05-22T01:03:29.630440+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKZXOXQU2Z7Z","created_at":"2026-05-22T01:03:29.630440+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKZXOXQU2Z7Z5TMN","created_at":"2026-05-22T01:03:29.630440+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKZXOXQU","created_at":"2026-05-22T01:03:29.630440+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/WKZXOXQU2Z7Z5TMNDYBKFLCMXK","json":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK.json","graph_json":"https://pith.science/api/pith-number/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/graph.json","events_json":"https://pith.science/api/pith-number/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/events.json","paper":"https://pith.science/paper/WKZXOXQU"},"agent_actions":{"view_html":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK","download_json":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK.json","view_paper":"https://pith.science/paper/WKZXOXQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21728&json=true","fetch_graph":"https://pith.science/api/pith-number/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/graph.json","fetch_events":"https://pith.science/api/pith-number/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/action/storage_attestation","attest_author":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/action/author_attestation","sign_citation":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/action/citation_signature","submit_replication":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/action/replication_record"}},"created_at":"2026-05-22T01:03:29.630440+00:00","updated_at":"2026-05-22T01:03:29.630440+00:00"}