{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WKZXOXQU2Z7Z5TMNDYBKFLCMXK","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":"cbf535b068a3684bdf02ec7958e0e9b175c7e1fa6bcdba19f024b52b4f89cd11","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T20:43:38Z","title_canon_sha256":"9c927717ab25f79663b9da931b2461c3f44248d83b62a9d519c5517a17ab3a9d"},"schema_version":"1.0","source":{"id":"2605.21728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21728","created_at":"2026-05-22T01:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21728v1","created_at":"2026-05-22T01:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21728","created_at":"2026-05-22T01:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"WKZXOXQU2Z7Z","created_at":"2026-05-22T01:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"WKZXOXQU2Z7Z5TMN","created_at":"2026-05-22T01:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"WKZXOXQU","created_at":"2026-05-22T01:03:29Z"}],"graph_snapshots":[{"event_id":"sha256:9b70fbd9cc33105e323cefc86501cc5f65c3f78e3ee077803ce1197f33540cd9","target":"graph","created_at":"2026-05-22T01:03:29Z","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/2605.21728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bruno Martins, Chrysoula Zerva, Gon\\c{c}alo Gomes","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T20:43:38Z","title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21728","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":"sha256:353f07cee66b4a767fab945ae5e029023619f0119ff0e9e915dbe2896bd06dcb","target":"record","created_at":"2026-05-22T01:03:29Z","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":"cbf535b068a3684bdf02ec7958e0e9b175c7e1fa6bcdba19f024b52b4f89cd11","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T20:43:38Z","title_canon_sha256":"9c927717ab25f79663b9da931b2461c3f44248d83b62a9d519c5517a17ab3a9d"},"schema_version":"1.0","source":{"id":"2605.21728","kind":"arxiv","version":1}},"canonical_sha256":"b2b3775e14d67f9ecd8d1e02a2ac4cba806d3c69eb4729c1a5d062e520b40a67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2b3775e14d67f9ecd8d1e02a2ac4cba806d3c69eb4729c1a5d062e520b40a67","first_computed_at":"2026-05-22T01:03:29.630334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:29.630334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CftgsoHtRzt1jnqGja1TxWwrFSPssMtRZcXnhvlL0oMLbmTi5ky6cQnG6NH3wEeLgth4u+WQmzMMYyDbXda9AA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:29.630995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:353f07cee66b4a767fab945ae5e029023619f0119ff0e9e915dbe2896bd06dcb","sha256:9b70fbd9cc33105e323cefc86501cc5f65c3f78e3ee077803ce1197f33540cd9"],"state_sha256":"6ba86e2fec1d4408cb808d74356298a84cd1cdbf2a95597b5b1e297182456cd4"}