{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R3LBS46ADLSTNAVX43RG6LZKSB","short_pith_number":"pith:R3LBS46A","canonical_record":{"source":{"id":"2502.09818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T23:29:01Z","cross_cats_sorted":[],"title_canon_sha256":"aa1a7bae306560f027b7e801bdcc434ff2888ad22dd116d7b407827760770afd","abstract_canon_sha256":"8d3f61e3415f135f5a91a0b92a4bbf7995a5b44b88f2f642c3e2ca29bae1581d"},"schema_version":"1.0"},"canonical_sha256":"8ed61973c01ae53682b7e6e26f2f2a904e87153c3d59b23af33e73a3a75ad204","source":{"kind":"arxiv","id":"2502.09818","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09818","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09818v1","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09818","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"R3LBS46ADLST","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"R3LBS46ADLSTNAVX","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"R3LBS46A","created_at":"2026-07-05T10:14:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R3LBS46ADLSTNAVX43RG6LZKSB","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T23:29:01Z","cross_cats_sorted":[],"title_canon_sha256":"aa1a7bae306560f027b7e801bdcc434ff2888ad22dd116d7b407827760770afd","abstract_canon_sha256":"8d3f61e3415f135f5a91a0b92a4bbf7995a5b44b88f2f642c3e2ca29bae1581d"},"schema_version":"1.0"},"canonical_sha256":"8ed61973c01ae53682b7e6e26f2f2a904e87153c3d59b23af33e73a3a75ad204","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:12.720856Z","signature_b64":"WSDDk622M5c9fShA7UnMx6fqiAULnJ1/9w4n+AcflgQWODHSk8TKmR7Kft1s9YPMP1IrmUJwGDO6o+J78ObXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ed61973c01ae53682b7e6e26f2f2a904e87153c3d59b23af33e73a3a75ad204","last_reissued_at":"2026-07-05T10:14:12.720361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:12.720361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09818","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":"2026-07-05T10:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SADO92a9lA+OuJEC1hz5O9tganTzwEmmrslqGHr+4f3rsmBVg1T0400B7+ftdHXCfS+/PPnxvXePmxHOXmHhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:52:24.796946Z"},"content_sha256":"39a21741d4aa447b689cdff25d7c46f9042fce22df8d64323f7782e0f4d6c798","schema_version":"1.0","event_id":"sha256:39a21741d4aa447b689cdff25d7c46f9042fce22df8d64323f7782e0f4d6c798"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R3LBS46ADLSTNAVX43RG6LZKSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the robustness of multimodal language model towards distractions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Chen, Jindong Wang, Ming Liu, Wensheng Zhang","submitted_at":"2025-02-13T23:29:01Z","abstract_excerpt":"Although vision-language models (VLMs) have achieved significant success in various applications such as visual question answering, their resilience to prompt variations remains an under-explored area. Understanding how distractions affect VLMs is crucial for improving their real-world applicability, as inputs could have noisy and irrelevant information in many practical scenarios. This paper aims to assess the robustness of VLMs against both visual and textual distractions in the context of science question answering. Built on the ScienceQA dataset, we developed a new benchmark that introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09818","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/2502.09818/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":"2026-07-05T10:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WxECjfPEj+SR/ToPoaMPOr0EJLjl3tMtk7pROuK1cfsTEyAWyEz76jM9G3Plt3juixVRG4IZKtPf8FpCEIeECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:52:24.797440Z"},"content_sha256":"8fb0179519372047923fac1d2c6a2eb304424abd1c537a3c5b2bccbfd0b3a9c1","schema_version":"1.0","event_id":"sha256:8fb0179519372047923fac1d2c6a2eb304424abd1c537a3c5b2bccbfd0b3a9c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3LBS46ADLSTNAVX43RG6LZKSB/bundle.json","state_url":"https://pith.science/pith/R3LBS46ADLSTNAVX43RG6LZKSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3LBS46ADLSTNAVX43RG6LZKSB/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":"2026-08-08T15:52:24Z","links":{"resolver":"https://pith.science/pith/R3LBS46ADLSTNAVX43RG6LZKSB","bundle":"https://pith.science/pith/R3LBS46ADLSTNAVX43RG6LZKSB/bundle.json","state":"https://pith.science/pith/R3LBS46ADLSTNAVX43RG6LZKSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3LBS46ADLSTNAVX43RG6LZKSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R3LBS46ADLSTNAVX43RG6LZKSB","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":"8d3f61e3415f135f5a91a0b92a4bbf7995a5b44b88f2f642c3e2ca29bae1581d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T23:29:01Z","title_canon_sha256":"aa1a7bae306560f027b7e801bdcc434ff2888ad22dd116d7b407827760770afd"},"schema_version":"1.0","source":{"id":"2502.09818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09818","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09818v1","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09818","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"R3LBS46ADLST","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"R3LBS46ADLSTNAVX","created_at":"2026-07-05T10:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"R3LBS46A","created_at":"2026-07-05T10:14:12Z"}],"graph_snapshots":[{"event_id":"sha256:8fb0179519372047923fac1d2c6a2eb304424abd1c537a3c5b2bccbfd0b3a9c1","target":"graph","created_at":"2026-07-05T10:14:12Z","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/2502.09818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although vision-language models (VLMs) have achieved significant success in various applications such as visual question answering, their resilience to prompt variations remains an under-explored area. Understanding how distractions affect VLMs is crucial for improving their real-world applicability, as inputs could have noisy and irrelevant information in many practical scenarios. This paper aims to assess the robustness of VLMs against both visual and textual distractions in the context of science question answering. Built on the ScienceQA dataset, we developed a new benchmark that introduce","authors_text":"Hao Chen, Jindong Wang, Ming Liu, Wensheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T23:29:01Z","title":"On the robustness of multimodal language model towards distractions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09818","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":"sha256:39a21741d4aa447b689cdff25d7c46f9042fce22df8d64323f7782e0f4d6c798","target":"record","created_at":"2026-07-05T10:14:12Z","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":"8d3f61e3415f135f5a91a0b92a4bbf7995a5b44b88f2f642c3e2ca29bae1581d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T23:29:01Z","title_canon_sha256":"aa1a7bae306560f027b7e801bdcc434ff2888ad22dd116d7b407827760770afd"},"schema_version":"1.0","source":{"id":"2502.09818","kind":"arxiv","version":1}},"canonical_sha256":"8ed61973c01ae53682b7e6e26f2f2a904e87153c3d59b23af33e73a3a75ad204","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ed61973c01ae53682b7e6e26f2f2a904e87153c3d59b23af33e73a3a75ad204","first_computed_at":"2026-07-05T10:14:12.720361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:12.720361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WSDDk622M5c9fShA7UnMx6fqiAULnJ1/9w4n+AcflgQWODHSk8TKmR7Kft1s9YPMP1IrmUJwGDO6o+J78ObXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:12.720856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39a21741d4aa447b689cdff25d7c46f9042fce22df8d64323f7782e0f4d6c798","sha256:8fb0179519372047923fac1d2c6a2eb304424abd1c537a3c5b2bccbfd0b3a9c1"],"state_sha256":"e284720d6a2bd38f99db0d1e74aeaa3885aca7f1ec6539d68e0afd130d351a3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOHY/m7RfCcUPJ+AEEnjMRvYtVMB2BDTRh9Wk3TMeSGvOSb8EbMwq64k5hWdeCFcXVUZf0oQJOgfy2h5CRVcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:52:24.802421Z","bundle_sha256":"3814a8ceecec31c1fb95ea2c3404146611898948308a9d948f794e4103028693"}}