{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WKZXOXQU2Z7Z5TMNDYBKFLCMXK","short_pith_number":"pith:WKZXOXQU","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"},"canonical_sha256":"b2b3775e14d67f9ecd8d1e02a2ac4cba806d3c69eb4729c1a5d062e520b40a67","source":{"kind":"arxiv","id":"2605.21728","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WKZXOXQU2Z7Z5TMNDYBKFLCMXK","target":"record","payload":{"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"},"canonical_sha256":"b2b3775e14d67f9ecd8d1e02a2ac4cba806d3c69eb4729c1a5d062e520b40a67","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"},"source_kind":"arxiv","source_id":"2605.21728","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SponNjn7sjjuh7BUBST17r2IWmTixmGW0jIiNyn79sMxdEXNIsH5VkNP6TFyfl5lT7FQO9h8Hgh4OD9VjaECAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:21:34.770791Z"},"content_sha256":"353f07cee66b4a767fab945ae5e029023619f0119ff0e9e915dbe2896bd06dcb","schema_version":"1.0","event_id":"sha256:353f07cee66b4a767fab945ae5e029023619f0119ff0e9e915dbe2896bd06dcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WKZXOXQU2Z7Z5TMNDYBKFLCMXK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXkS03jcnqxQax8JdvvWZDOYqiihzK/EdX22inu/lnOQhWzkDnT6DLglf0XBupjp3ZfPhXtAeZCWCcclfFhQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:21:34.771250Z"},"content_sha256":"9b70fbd9cc33105e323cefc86501cc5f65c3f78e3ee077803ce1197f33540cd9","schema_version":"1.0","event_id":"sha256:9b70fbd9cc33105e323cefc86501cc5f65c3f78e3ee077803ce1197f33540cd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/bundle.json","state_url":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T00:21:34Z","links":{"resolver":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK","bundle":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/bundle.json","state":"https://pith.science/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKZXOXQU2Z7Z5TMNDYBKFLCMXK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdLPnEY2Y5oIMn9WdaaL7A62Og5SbC2o2RNiG6Avvy5nVPiA0zAn51fEzugCCOXwYR3dPxxCYbLONR1qR2PxAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:21:34.774371Z","bundle_sha256":"fe06e0d9d539f648bde9a6b30bf1e5ebcf3c592988a065c533dd604f2363942d"}}