{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M2D6WO3S6U7EZ3DIAHUCZGGSRV","short_pith_number":"pith:M2D6WO3S","canonical_record":{"source":{"id":"2408.01363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-08-02T16:15:25Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"title_canon_sha256":"a48c38a406bfd620a49e39c9eb1c405e1240f29e98dba2b30c4162d292afa2eb","abstract_canon_sha256":"d0b77294b67f7d5abe34a18fbefdc3874fffe0c9de480af5e5c0544062b06596"},"schema_version":"1.0"},"canonical_sha256":"6687eb3b72f53e4cec6801e82c98d28d639b9a95fd0a3eccded3df7592518000","source":{"kind":"arxiv","id":"2408.01363","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01363","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01363v1","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01363","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"pith_short_12","alias_value":"M2D6WO3S6U7E","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"pith_short_16","alias_value":"M2D6WO3S6U7EZ3DI","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"pith_short_8","alias_value":"M2D6WO3S","created_at":"2026-07-05T08:51:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M2D6WO3S6U7EZ3DIAHUCZGGSRV","target":"record","payload":{"canonical_record":{"source":{"id":"2408.01363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-08-02T16:15:25Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"title_canon_sha256":"a48c38a406bfd620a49e39c9eb1c405e1240f29e98dba2b30c4162d292afa2eb","abstract_canon_sha256":"d0b77294b67f7d5abe34a18fbefdc3874fffe0c9de480af5e5c0544062b06596"},"schema_version":"1.0"},"canonical_sha256":"6687eb3b72f53e4cec6801e82c98d28d639b9a95fd0a3eccded3df7592518000","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:30.624188Z","signature_b64":"W7YzIPqIwEmw+eQ+BKRny+GPavDoReGt4xgIJ36fXz+DX46eE9imKYzAjEZqStU2z8AQl39+J5DTtaCpexcGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6687eb3b72f53e4cec6801e82c98d28d639b9a95fd0a3eccded3df7592518000","last_reissued_at":"2026-07-05T08:51:30.623683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:30.623683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.01363","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":"2026-07-05T08:51:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mSvkK/TVQ3B6g2A9ZW1lISsE5rXMv78lJmrWJ1Mt3PbiI3FVTJ/gGtbQEdIvNjbr0DNhchU6TS0JAKDuagq2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:00:35.404640Z"},"content_sha256":"0536ae7f9fcfebd504363c1d40283eec946a23bbd50bc1bc81a3eb442db122b3","schema_version":"1.0","event_id":"sha256:0536ae7f9fcfebd504363c1d40283eec946a23bbd50bc1bc81a3eb442db122b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M2D6WO3S6U7EZ3DIAHUCZGGSRV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM"],"primary_cat":"cs.IR","authors_text":"Jheng-Hong Yang, Jimmy Lin","submitted_at":"2024-08-02T16:15:25Z","abstract_excerpt":"Vision--Language Models (VLMs) have demonstrated success across diverse applications, yet their potential to assist in relevance judgments remains uncertain. This paper assesses the relevance estimation capabilities of VLMs, including CLIP, LLaVA, and GPT-4V, within a large-scale \\textit{ad hoc} retrieval task tailored for multimedia content creation in a zero-shot fashion. Preliminary experiments reveal the following: (1) Both LLaVA and GPT-4V, encompassing open-source and closed-source visual-instruction-tuned Large Language Models (LLMs), achieve notable Kendall's $\\tau \\sim 0.4$ when compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01363","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/2408.01363/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":"2026-07-05T08:51:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvD3lgHe2HbV7FETZYqwBQMX2qb5ovDfQIWG3aGRMSVzxlHJgCaaaGruENpfjKgL5E23NQWthRnUFY4MpuFaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:00:35.405555Z"},"content_sha256":"45e4ff1a1d26854f555aacafc33195a51af1a8971d3a833bfaf15181cdab11a6","schema_version":"1.0","event_id":"sha256:45e4ff1a1d26854f555aacafc33195a51af1a8971d3a833bfaf15181cdab11a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2D6WO3S6U7EZ3DIAHUCZGGSRV/bundle.json","state_url":"https://pith.science/pith/M2D6WO3S6U7EZ3DIAHUCZGGSRV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2D6WO3S6U7EZ3DIAHUCZGGSRV/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":"2026-08-17T05:00:35Z","links":{"resolver":"https://pith.science/pith/M2D6WO3S6U7EZ3DIAHUCZGGSRV","bundle":"https://pith.science/pith/M2D6WO3S6U7EZ3DIAHUCZGGSRV/bundle.json","state":"https://pith.science/pith/M2D6WO3S6U7EZ3DIAHUCZGGSRV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2D6WO3S6U7EZ3DIAHUCZGGSRV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M2D6WO3S6U7EZ3DIAHUCZGGSRV","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":"d0b77294b67f7d5abe34a18fbefdc3874fffe0c9de480af5e5c0544062b06596","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-08-02T16:15:25Z","title_canon_sha256":"a48c38a406bfd620a49e39c9eb1c405e1240f29e98dba2b30c4162d292afa2eb"},"schema_version":"1.0","source":{"id":"2408.01363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01363","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01363v1","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01363","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"pith_short_12","alias_value":"M2D6WO3S6U7E","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"pith_short_16","alias_value":"M2D6WO3S6U7EZ3DI","created_at":"2026-07-05T08:51:30Z"},{"alias_kind":"pith_short_8","alias_value":"M2D6WO3S","created_at":"2026-07-05T08:51:30Z"}],"graph_snapshots":[{"event_id":"sha256:45e4ff1a1d26854f555aacafc33195a51af1a8971d3a833bfaf15181cdab11a6","target":"graph","created_at":"2026-07-05T08:51:30Z","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/2408.01363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision--Language Models (VLMs) have demonstrated success across diverse applications, yet their potential to assist in relevance judgments remains uncertain. This paper assesses the relevance estimation capabilities of VLMs, including CLIP, LLaVA, and GPT-4V, within a large-scale \\textit{ad hoc} retrieval task tailored for multimedia content creation in a zero-shot fashion. Preliminary experiments reveal the following: (1) Both LLaVA and GPT-4V, encompassing open-source and closed-source visual-instruction-tuned Large Language Models (LLMs), achieve notable Kendall's $\\tau \\sim 0.4$ when compa","authors_text":"Jheng-Hong Yang, Jimmy Lin","cross_cats":["cs.CL","cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-08-02T16:15:25Z","title":"Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01363","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":"sha256:0536ae7f9fcfebd504363c1d40283eec946a23bbd50bc1bc81a3eb442db122b3","target":"record","created_at":"2026-07-05T08:51:30Z","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":"d0b77294b67f7d5abe34a18fbefdc3874fffe0c9de480af5e5c0544062b06596","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-08-02T16:15:25Z","title_canon_sha256":"a48c38a406bfd620a49e39c9eb1c405e1240f29e98dba2b30c4162d292afa2eb"},"schema_version":"1.0","source":{"id":"2408.01363","kind":"arxiv","version":1}},"canonical_sha256":"6687eb3b72f53e4cec6801e82c98d28d639b9a95fd0a3eccded3df7592518000","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6687eb3b72f53e4cec6801e82c98d28d639b9a95fd0a3eccded3df7592518000","first_computed_at":"2026-07-05T08:51:30.623683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:30.623683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W7YzIPqIwEmw+eQ+BKRny+GPavDoReGt4xgIJ36fXz+DX46eE9imKYzAjEZqStU2z8AQl39+J5DTtaCpexcGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:30.624188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0536ae7f9fcfebd504363c1d40283eec946a23bbd50bc1bc81a3eb442db122b3","sha256:45e4ff1a1d26854f555aacafc33195a51af1a8971d3a833bfaf15181cdab11a6"],"state_sha256":"3015df7aa4478fe7c4f923c001e85b4802813c99295444f9013dab4f230347b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MNowjNVm8Yt6PuzeTnlUiATI5nf2PZ3UEmGzbWjZJjK79N31PAPCN1r3/TbaA0LyzXnKlMHfVctpuGX3QMwmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T05:00:35.429994Z","bundle_sha256":"1c5e00872aac054ddf1bae60aeec553b1964d1039458637a37f16a5876f884c5"}}