{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XJ6HIL3O2Q2C6KWUT7LE4XDRXB","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":"2444bbbf23457ae824d906fc64af5c111702b996c77d6bd8d10dddcf68c2c7cf","cross_cats_sorted":["cs.AI","cs.LG","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T09:07:14Z","title_canon_sha256":"e4d029a3de4cdc18fc6852cb698417811da4cd5cc9866285706ceebaa6e13dfd"},"schema_version":"1.0","source":{"id":"2403.09193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09193","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09193v2","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09193","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"pith_short_12","alias_value":"XJ6HIL3O2Q2C","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"pith_short_16","alias_value":"XJ6HIL3O2Q2C6KWU","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"pith_short_8","alias_value":"XJ6HIL3O","created_at":"2026-07-05T10:25:05Z"}],"graph_snapshots":[{"event_id":"sha256:dd95fa4cb4689afeed7ba30915f169c3f19b15aec24f37cebe65c514d64d6ecc","target":"graph","created_at":"2026-07-05T10:25:05Z","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/2403.09193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model (LLM) with a vision encoder. However, both the LLM and the vision encoder come with their own set of biases, cue preferences, and shortcuts, which have been rigorously studied in uni-modal models. A timely question is how such (potentially misaligned) biases and cue preferences behave under multi-modal fusion in VLMs. As a first step towards a better understanding, we investigate a particularly well-studied vision-on","authors_text":"Janis Keuper, Jovita Lukasik, Margret Keuper, M. Jehanzeb Mirza, Paul Gavrikov, Robert Geirhos, Steffen Jung","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T09:07:14Z","title":"Can We Talk Models Into Seeing the World Differently?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09193","kind":"arxiv","version":2},"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:d21a76c4b202b0ac5df60f6aa3bfe9c1596b5bb2bd2af76cc34140fc380eecd1","target":"record","created_at":"2026-07-05T10:25:05Z","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":"2444bbbf23457ae824d906fc64af5c111702b996c77d6bd8d10dddcf68c2c7cf","cross_cats_sorted":["cs.AI","cs.LG","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T09:07:14Z","title_canon_sha256":"e4d029a3de4cdc18fc6852cb698417811da4cd5cc9866285706ceebaa6e13dfd"},"schema_version":"1.0","source":{"id":"2403.09193","kind":"arxiv","version":2}},"canonical_sha256":"ba7c742f6ed4342f2ad49fd64e5c71b8409a28dc64d931cb839aebe14b28e7bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba7c742f6ed4342f2ad49fd64e5c71b8409a28dc64d931cb839aebe14b28e7bf","first_computed_at":"2026-07-05T10:25:05.140930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:05.140930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5BPidQnoL9meOhN29fugYNJWRU3UkqPw/E58ReM3hMvAaENSzANd8UP9Py1sHCBBxuFAe1yLRONXQOD0GRPKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:05.141882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d21a76c4b202b0ac5df60f6aa3bfe9c1596b5bb2bd2af76cc34140fc380eecd1","sha256:dd95fa4cb4689afeed7ba30915f169c3f19b15aec24f37cebe65c514d64d6ecc"],"state_sha256":"946433428c907445c8954c1ab57688c2c1c13b68ee88cc4593f4594669992717"}