{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I74232CRWJCUOYIXLHUGLTLEIC","short_pith_number":"pith:I74232CR","canonical_record":{"source":{"id":"2508.05602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T17:42:44Z","cross_cats_sorted":[],"title_canon_sha256":"feccb9b31837ff6dd2a0bd51244fcd3bbfbecd75e316246f409aaf66505e22cf","abstract_canon_sha256":"9d3f0ca56e7d18d1eaf57ae8e0d2c84edd8f475d28856105a9f97f4bfae89cef"},"schema_version":"1.0"},"canonical_sha256":"47f9ade851b24547611759e865cd6440912d1594a12a790069cd230035f764f4","source":{"kind":"arxiv","id":"2508.05602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05602","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05602v1","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05602","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"I74232CRWJCU","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_16","alias_value":"I74232CRWJCUOYIX","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_8","alias_value":"I74232CR","created_at":"2026-07-05T11:50:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I74232CRWJCUOYIXLHUGLTLEIC","target":"record","payload":{"canonical_record":{"source":{"id":"2508.05602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T17:42:44Z","cross_cats_sorted":[],"title_canon_sha256":"feccb9b31837ff6dd2a0bd51244fcd3bbfbecd75e316246f409aaf66505e22cf","abstract_canon_sha256":"9d3f0ca56e7d18d1eaf57ae8e0d2c84edd8f475d28856105a9f97f4bfae89cef"},"schema_version":"1.0"},"canonical_sha256":"47f9ade851b24547611759e865cd6440912d1594a12a790069cd230035f764f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:22.307330Z","signature_b64":"q7p9DS4jj2zTyiJbZE3GYFGmyVN7sIuim9EZ3rTgMy2C7VsD+AY4MliksPnNRvZ0juqJc0xRs2Fd6KPn1h2dDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f9ade851b24547611759e865cd6440912d1594a12a790069cd230035f764f4","last_reissued_at":"2026-07-05T11:50:22.306884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:22.306884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.05602","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":"2026-07-05T11:50:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lU4EkvvRavKrfTVdhezvgpz+G58UpnW4WLHcGN50xxoF/fFZCtQR1EQLEDueliCSAB9a/mCG8+PxWNtsytMNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:21:25.501583Z"},"content_sha256":"77a06c763af91286f5bfa48e64259b138f0ce9bad7484035d74a76b6f7fd1bca","schema_version":"1.0","event_id":"sha256:77a06c763af91286f5bfa48e64259b138f0ce9bad7484035d74a76b6f7fd1bca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I74232CRWJCUOYIXLHUGLTLEIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinjin Li, Lan Ma, Oliver Liu, Tao Sun","submitted_at":"2025-08-07T17:42:44Z","abstract_excerpt":"Multimodal generative AI usually involves generating image or text responses given inputs in another modality. The evaluation of image-text relevancy is essential for measuring response quality or ranking candidate responses. In particular, binary relevancy evaluation, i.e., ``Relevant'' vs. ``Not Relevant'', is a fundamental problem. However, this is a challenging task considering that texts have diverse formats and the definition of relevancy varies in different scenarios. We find that Multimodal Large Language Models (MLLMs) are an ideal choice to build such evaluators, as they can flexibly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05602","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/2508.05602/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":"2026-07-05T11:50:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enK2mzhPIAoie6jg1C1KKHsGDJ0VTnuPajzTjgaB6HGoQcpi7cPATmOG1yDI1H7QZhiY2RzylgJsyReb4hzTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:21:25.502098Z"},"content_sha256":"2fcc23824f325f4277a7df10c1aef0edf7e42cb0677356fee84786d27cd4d4b7","schema_version":"1.0","event_id":"sha256:2fcc23824f325f4277a7df10c1aef0edf7e42cb0677356fee84786d27cd4d4b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I74232CRWJCUOYIXLHUGLTLEIC/bundle.json","state_url":"https://pith.science/pith/I74232CRWJCUOYIXLHUGLTLEIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I74232CRWJCUOYIXLHUGLTLEIC/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":"2026-08-08T16:21:25Z","links":{"resolver":"https://pith.science/pith/I74232CRWJCUOYIXLHUGLTLEIC","bundle":"https://pith.science/pith/I74232CRWJCUOYIXLHUGLTLEIC/bundle.json","state":"https://pith.science/pith/I74232CRWJCUOYIXLHUGLTLEIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I74232CRWJCUOYIXLHUGLTLEIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I74232CRWJCUOYIXLHUGLTLEIC","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":"9d3f0ca56e7d18d1eaf57ae8e0d2c84edd8f475d28856105a9f97f4bfae89cef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T17:42:44Z","title_canon_sha256":"feccb9b31837ff6dd2a0bd51244fcd3bbfbecd75e316246f409aaf66505e22cf"},"schema_version":"1.0","source":{"id":"2508.05602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05602","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05602v1","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05602","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"I74232CRWJCU","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_16","alias_value":"I74232CRWJCUOYIX","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_8","alias_value":"I74232CR","created_at":"2026-07-05T11:50:22Z"}],"graph_snapshots":[{"event_id":"sha256:2fcc23824f325f4277a7df10c1aef0edf7e42cb0677356fee84786d27cd4d4b7","target":"graph","created_at":"2026-07-05T11:50:22Z","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/2508.05602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal generative AI usually involves generating image or text responses given inputs in another modality. The evaluation of image-text relevancy is essential for measuring response quality or ranking candidate responses. In particular, binary relevancy evaluation, i.e., ``Relevant'' vs. ``Not Relevant'', is a fundamental problem. However, this is a challenging task considering that texts have diverse formats and the definition of relevancy varies in different scenarios. We find that Multimodal Large Language Models (MLLMs) are an ideal choice to build such evaluators, as they can flexibly","authors_text":"Jinjin Li, Lan Ma, Oliver Liu, Tao Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T17:42:44Z","title":"LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05602","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":"sha256:77a06c763af91286f5bfa48e64259b138f0ce9bad7484035d74a76b6f7fd1bca","target":"record","created_at":"2026-07-05T11:50:22Z","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":"9d3f0ca56e7d18d1eaf57ae8e0d2c84edd8f475d28856105a9f97f4bfae89cef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T17:42:44Z","title_canon_sha256":"feccb9b31837ff6dd2a0bd51244fcd3bbfbecd75e316246f409aaf66505e22cf"},"schema_version":"1.0","source":{"id":"2508.05602","kind":"arxiv","version":1}},"canonical_sha256":"47f9ade851b24547611759e865cd6440912d1594a12a790069cd230035f764f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47f9ade851b24547611759e865cd6440912d1594a12a790069cd230035f764f4","first_computed_at":"2026-07-05T11:50:22.306884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:22.306884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q7p9DS4jj2zTyiJbZE3GYFGmyVN7sIuim9EZ3rTgMy2C7VsD+AY4MliksPnNRvZ0juqJc0xRs2Fd6KPn1h2dDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:22.307330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77a06c763af91286f5bfa48e64259b138f0ce9bad7484035d74a76b6f7fd1bca","sha256:2fcc23824f325f4277a7df10c1aef0edf7e42cb0677356fee84786d27cd4d4b7"],"state_sha256":"e1a627a0989408e922075ca686e621d25aad8eea84974d6c3afb20f60e660424"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4/o5tGoAYD0vMcDwJ5/JS6ETFF70+HffZv1o1Wiitb7Ny0elnChu2El1X1zrPyBVcmg5Yux44FuYm6og4AkCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:21:25.506410Z","bundle_sha256":"3417a2ecc1f8cabeb0cbccff0a4c9498255be46beae02590991a883923c2824b"}}