{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2MMUHDPF4XE2PNY2CYA5RV5KQT","short_pith_number":"pith:2MMUHDPF","canonical_record":{"source":{"id":"2404.18624","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T11:52:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"088ee780a06bc9fe37fca9a22d0d8177efce862ad5ef71996eea2998f0989080","abstract_canon_sha256":"b3f384fea3ced2dcc2a9d8463a11e316e30edb2fb91d6010ec7fd535006b0cb8"},"schema_version":"1.0"},"canonical_sha256":"d319438de5e5c9a7b71a1601d8d7aa84f0b1f0dac00a467fa28d56b61780a706","source":{"kind":"arxiv","id":"2404.18624","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18624","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18624v4","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18624","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"pith_short_12","alias_value":"2MMUHDPF4XE2","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"pith_short_16","alias_value":"2MMUHDPF4XE2PNY2","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"pith_short_8","alias_value":"2MMUHDPF","created_at":"2026-07-05T10:57:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2MMUHDPF4XE2PNY2CYA5RV5KQT","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18624","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T11:52:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"088ee780a06bc9fe37fca9a22d0d8177efce862ad5ef71996eea2998f0989080","abstract_canon_sha256":"b3f384fea3ced2dcc2a9d8463a11e316e30edb2fb91d6010ec7fd535006b0cb8"},"schema_version":"1.0"},"canonical_sha256":"d319438de5e5c9a7b71a1601d8d7aa84f0b1f0dac00a467fa28d56b61780a706","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:26.917720Z","signature_b64":"ce8x/bt/Y+9Br3X8tv0K9wf1PFEQvGh5Z0Rf5DV94jlafhhGMG1KXrJLahuc7EIp0a86N0VFZj0g1RYkDkp5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d319438de5e5c9a7b71a1601d8d7aa84f0b1f0dac00a467fa28d56b61780a706","last_reissued_at":"2026-07-05T10:57:26.917227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:26.917227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18624","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GubRa/Kz/M8jWdtRAgkEu2xptMfb9jCbfYAU5KiS5sepTH2xFfYazn1MfhnFNTf1hKqf6h43FZUy8z+PzXaGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T07:55:55.727051Z"},"content_sha256":"b1837a73d153ca4d9a7ef80d676eac2dc479d0b41dddb7915ffb38051e30adcc","schema_version":"1.0","event_id":"sha256:b1837a73d153ca4d9a7ef80d676eac2dc479d0b41dddb7915ffb38051e30adcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2MMUHDPF4XE2PNY2CYA5RV5KQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anette Frank, Letitia Parcalabescu","submitted_at":"2024-04-29T11:52:20Z","abstract_excerpt":"Vision and language model (VLM) decoders are currently the best-performing architectures on multimodal tasks. Next to answers, they are able to produce natural language explanations, either in post-hoc or CoT settings. However, it is not clear to what extent they are using the input vision and text modalities when generating answers or explanations. In this work, we investigate if VLMs rely on their input modalities differently when they produce explanations as opposed to answers. We also evaluate the self-consistency of VLM decoders in both post-hoc and CoT explanation settings, by extending "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18624","kind":"arxiv","version":4},"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/2404.18624/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":"2026-07-05T10:57:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1pHR9VHSJDSRNnNrCfI4uJrlwNP8ZiwgPYaPGaeV3fok6by3rS9KUqeda5DgL77na/fMGVtmYCguWk22bd1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T07:55:55.727443Z"},"content_sha256":"97b096706eaf3770be2d0a4a1b086c224bb06c2dea42188c33c8c80694bd5463","schema_version":"1.0","event_id":"sha256:97b096706eaf3770be2d0a4a1b086c224bb06c2dea42188c33c8c80694bd5463"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MMUHDPF4XE2PNY2CYA5RV5KQT/bundle.json","state_url":"https://pith.science/pith/2MMUHDPF4XE2PNY2CYA5RV5KQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MMUHDPF4XE2PNY2CYA5RV5KQT/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":"2026-07-16T07:55:55Z","links":{"resolver":"https://pith.science/pith/2MMUHDPF4XE2PNY2CYA5RV5KQT","bundle":"https://pith.science/pith/2MMUHDPF4XE2PNY2CYA5RV5KQT/bundle.json","state":"https://pith.science/pith/2MMUHDPF4XE2PNY2CYA5RV5KQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MMUHDPF4XE2PNY2CYA5RV5KQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2MMUHDPF4XE2PNY2CYA5RV5KQT","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":"b3f384fea3ced2dcc2a9d8463a11e316e30edb2fb91d6010ec7fd535006b0cb8","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T11:52:20Z","title_canon_sha256":"088ee780a06bc9fe37fca9a22d0d8177efce862ad5ef71996eea2998f0989080"},"schema_version":"1.0","source":{"id":"2404.18624","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18624","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18624v4","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18624","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"pith_short_12","alias_value":"2MMUHDPF4XE2","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"pith_short_16","alias_value":"2MMUHDPF4XE2PNY2","created_at":"2026-07-05T10:57:26Z"},{"alias_kind":"pith_short_8","alias_value":"2MMUHDPF","created_at":"2026-07-05T10:57:26Z"}],"graph_snapshots":[{"event_id":"sha256:97b096706eaf3770be2d0a4a1b086c224bb06c2dea42188c33c8c80694bd5463","target":"graph","created_at":"2026-07-05T10:57:26Z","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/2404.18624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision and language model (VLM) decoders are currently the best-performing architectures on multimodal tasks. Next to answers, they are able to produce natural language explanations, either in post-hoc or CoT settings. However, it is not clear to what extent they are using the input vision and text modalities when generating answers or explanations. In this work, we investigate if VLMs rely on their input modalities differently when they produce explanations as opposed to answers. We also evaluate the self-consistency of VLM decoders in both post-hoc and CoT explanation settings, by extending ","authors_text":"Anette Frank, Letitia Parcalabescu","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T11:52:20Z","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18624","kind":"arxiv","version":4},"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:b1837a73d153ca4d9a7ef80d676eac2dc479d0b41dddb7915ffb38051e30adcc","target":"record","created_at":"2026-07-05T10:57:26Z","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":"b3f384fea3ced2dcc2a9d8463a11e316e30edb2fb91d6010ec7fd535006b0cb8","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T11:52:20Z","title_canon_sha256":"088ee780a06bc9fe37fca9a22d0d8177efce862ad5ef71996eea2998f0989080"},"schema_version":"1.0","source":{"id":"2404.18624","kind":"arxiv","version":4}},"canonical_sha256":"d319438de5e5c9a7b71a1601d8d7aa84f0b1f0dac00a467fa28d56b61780a706","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d319438de5e5c9a7b71a1601d8d7aa84f0b1f0dac00a467fa28d56b61780a706","first_computed_at":"2026-07-05T10:57:26.917227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:26.917227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ce8x/bt/Y+9Br3X8tv0K9wf1PFEQvGh5Z0Rf5DV94jlafhhGMG1KXrJLahuc7EIp0a86N0VFZj0g1RYkDkp5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:26.917720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18624","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1837a73d153ca4d9a7ef80d676eac2dc479d0b41dddb7915ffb38051e30adcc","sha256:97b096706eaf3770be2d0a4a1b086c224bb06c2dea42188c33c8c80694bd5463"],"state_sha256":"cc3bb44571615191817ed30120028ad38040f5321dae7328675edab3e3623bef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iYGrtsHhxqD0Nh4sCTEoTjLox02LREkBtKvu6SEJwhJ7RBoRxP69OmEggWZAQclSHsm3mECfFZHlbZXe2ygXCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T07:55:55.729990Z","bundle_sha256":"f92e05d8ec0420871671690ee6d7770ebdd30c8f911258b440439cd1a8a93b85"}}