{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JB6PKEABZCG2O6JZ2AUIJCYD7O","short_pith_number":"pith:JB6PKEAB","canonical_record":{"source":{"id":"2402.03757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T06:48:46Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1e5f088b01c3b41257e9706a8fb6c7317ca595d5cecc97defe8a81eace644ffb","abstract_canon_sha256":"738de84a17d6e90638b7be123939f14193452a5c726304a707f062522d995434"},"schema_version":"1.0"},"canonical_sha256":"487cf51001c88da77939d028848b03fba7e6f3dd2bf5e59692cb5c7b2c852c7c","source":{"kind":"arxiv","id":"2402.03757","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03757","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03757v2","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03757","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"JB6PKEABZCG2","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"JB6PKEABZCG2O6JZ","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"JB6PKEAB","created_at":"2026-07-05T09:15:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JB6PKEABZCG2O6JZ2AUIJCYD7O","target":"record","payload":{"canonical_record":{"source":{"id":"2402.03757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T06:48:46Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1e5f088b01c3b41257e9706a8fb6c7317ca595d5cecc97defe8a81eace644ffb","abstract_canon_sha256":"738de84a17d6e90638b7be123939f14193452a5c726304a707f062522d995434"},"schema_version":"1.0"},"canonical_sha256":"487cf51001c88da77939d028848b03fba7e6f3dd2bf5e59692cb5c7b2c852c7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:08.095279Z","signature_b64":"elu0zuArAATJUc/+ol67cQmdOSL3qy57wTW/rMrtfnIsZDHXN0xopIG7oQPyIv78NXpSa3CYcgpjcxqmFC2bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"487cf51001c88da77939d028848b03fba7e6f3dd2bf5e59692cb5c7b2c852c7c","last_reissued_at":"2026-07-05T09:15:08.094830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:08.094830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.03757","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NtEOta78xJCDQPlglnbLakdKTjFaJdop2wbQLOuWhq+s6/Q+s0qR+YQ2wNXkSQSxT8PJ/7Y7BwSuE7iC4mbkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:00:03.287212Z"},"content_sha256":"831eb247b4ac350df8685322dc3731394e5a5e6e6834b87b71877fa2db4676b1","schema_version":"1.0","event_id":"sha256:831eb247b4ac350df8685322dc3731394e5a5e6e6834b87b71877fa2db4676b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JB6PKEABZCG2O6JZ2AUIJCYD7O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Instinctive Bias: Spurious Images lead to Illusion in MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jipeng Zhang, Qing Lian, Renjie Pi, Rui Pan, Shizhe Diao, Tianyang Han, Tong Zhang, Yong Lin","submitted_at":"2024-02-06T06:48:46Z","abstract_excerpt":"Large language models (LLMs) have recently experienced remarkable progress, where the advent of multi-modal large language models (MLLMs) has endowed LLMs with visual capabilities, leading to impressive performances in various multi-modal tasks. However, those powerful MLLMs such as GPT-4V still fail spectacularly when presented with certain image and text inputs. In this paper, we identify a typical class of inputs that baffles MLLMs, which consist of images that are highly relevant but inconsistent with answers, causing MLLMs to suffer from visual illusion. To quantify the effect, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03757","kind":"arxiv","version":2},"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/2402.03757/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":"2026-07-05T09:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9r3M5wv/9VDQtW50YF1t13jB+cfbHlIZmXqNCRLpX1jvl1Tw4qMylnH8cCUsdQTbD25gHRKiBGGKXkZiYpL/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:00:03.287887Z"},"content_sha256":"aec0d010719f866182c70fd9acdda2f0065b5f83d27066a46567c60a26f64673","schema_version":"1.0","event_id":"sha256:aec0d010719f866182c70fd9acdda2f0065b5f83d27066a46567c60a26f64673"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JB6PKEABZCG2O6JZ2AUIJCYD7O/bundle.json","state_url":"https://pith.science/pith/JB6PKEABZCG2O6JZ2AUIJCYD7O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JB6PKEABZCG2O6JZ2AUIJCYD7O/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":"2026-08-07T21:00:03Z","links":{"resolver":"https://pith.science/pith/JB6PKEABZCG2O6JZ2AUIJCYD7O","bundle":"https://pith.science/pith/JB6PKEABZCG2O6JZ2AUIJCYD7O/bundle.json","state":"https://pith.science/pith/JB6PKEABZCG2O6JZ2AUIJCYD7O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JB6PKEABZCG2O6JZ2AUIJCYD7O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JB6PKEABZCG2O6JZ2AUIJCYD7O","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":"738de84a17d6e90638b7be123939f14193452a5c726304a707f062522d995434","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T06:48:46Z","title_canon_sha256":"1e5f088b01c3b41257e9706a8fb6c7317ca595d5cecc97defe8a81eace644ffb"},"schema_version":"1.0","source":{"id":"2402.03757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03757","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03757v2","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03757","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"JB6PKEABZCG2","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"JB6PKEABZCG2O6JZ","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"JB6PKEAB","created_at":"2026-07-05T09:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:aec0d010719f866182c70fd9acdda2f0065b5f83d27066a46567c60a26f64673","target":"graph","created_at":"2026-07-05T09:15:08Z","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/2402.03757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently experienced remarkable progress, where the advent of multi-modal large language models (MLLMs) has endowed LLMs with visual capabilities, leading to impressive performances in various multi-modal tasks. However, those powerful MLLMs such as GPT-4V still fail spectacularly when presented with certain image and text inputs. In this paper, we identify a typical class of inputs that baffles MLLMs, which consist of images that are highly relevant but inconsistent with answers, causing MLLMs to suffer from visual illusion. To quantify the effect, we propose","authors_text":"Jipeng Zhang, Qing Lian, Renjie Pi, Rui Pan, Shizhe Diao, Tianyang Han, Tong Zhang, Yong Lin","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T06:48:46Z","title":"The Instinctive Bias: Spurious Images lead to Illusion in MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03757","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":"sha256:831eb247b4ac350df8685322dc3731394e5a5e6e6834b87b71877fa2db4676b1","target":"record","created_at":"2026-07-05T09:15:08Z","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":"738de84a17d6e90638b7be123939f14193452a5c726304a707f062522d995434","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T06:48:46Z","title_canon_sha256":"1e5f088b01c3b41257e9706a8fb6c7317ca595d5cecc97defe8a81eace644ffb"},"schema_version":"1.0","source":{"id":"2402.03757","kind":"arxiv","version":2}},"canonical_sha256":"487cf51001c88da77939d028848b03fba7e6f3dd2bf5e59692cb5c7b2c852c7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"487cf51001c88da77939d028848b03fba7e6f3dd2bf5e59692cb5c7b2c852c7c","first_computed_at":"2026-07-05T09:15:08.094830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:08.094830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"elu0zuArAATJUc/+ol67cQmdOSL3qy57wTW/rMrtfnIsZDHXN0xopIG7oQPyIv78NXpSa3CYcgpjcxqmFC2bAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:08.095279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:831eb247b4ac350df8685322dc3731394e5a5e6e6834b87b71877fa2db4676b1","sha256:aec0d010719f866182c70fd9acdda2f0065b5f83d27066a46567c60a26f64673"],"state_sha256":"d9da719f73e9e11dead4220bcee1e1844b640c58e404b398e19d337e835bd08d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8d2n2zOJxkQncczO2v1ilyalDiLccvk8tsLyx2FKcpsQtcmTGE17GJp5OqumOJswB9B8BORAv7tTzoul9LHiCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:00:03.294271Z","bundle_sha256":"51e5bd20cc372ce05f7bd73f4af2925a88524d630ff4cb6f52dfe3195ee6231a"}}