{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6YT3CTJTDHJGHI5TZM2NHASE6B","short_pith_number":"pith:6YT3CTJT","schema_version":"1.0","canonical_sha256":"f627b14d3319d263a3b3cb34d38244f07bce5882d4e5420284e15027d13e8a48","source":{"kind":"arxiv","id":"2409.01151","version":1},"attestation_state":"computed","paper":{"title":"Understanding Multimodal Hallucination with Parameter-Free Representation Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Huishuai Zhang, Jianxin Liang, Yueqian Wang, Yuxuan Wang","submitted_at":"2024-09-02T10:37:26Z","abstract_excerpt":"Hallucination is a common issue in Multimodal Large Language Models (MLLMs), yet the underlying principles remain poorly understood. In this paper, we investigate which components of MLLMs contribute to object hallucinations. To analyze image representations while completely avoiding the influence of all other factors other than the image representation itself, we propose a parametric-free representation alignment metric (Pfram) that can measure the similarities between any two representation systems without requiring additional training parameters. Notably, Pfram can also assess the alignment"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.01151","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-02T10:37:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a8d9eb0df8efdb54074d538d3ebe3ce487c8d2ff8ce98fe496a9b8360cdad75a","abstract_canon_sha256":"e95fd3f7609aaa5c37324e47620c4634b849527eeb5d2d53b8829a69af287086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:59.695347Z","signature_b64":"KB4psRZ3YidkfaYHjQrl3eq5QUlDr4ynRS8sUrwKc5t4tHhKjCYLKnVKFc3fa2i66Vs1+12vadZpDjS3hPQBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f627b14d3319d263a3b3cb34d38244f07bce5882d4e5420284e15027d13e8a48","last_reissued_at":"2026-07-05T09:01:59.694839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:59.694839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Multimodal Hallucination with Parameter-Free Representation Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongyan Zhao, Huishuai Zhang, Jianxin Liang, Yueqian Wang, Yuxuan Wang","submitted_at":"2024-09-02T10:37:26Z","abstract_excerpt":"Hallucination is a common issue in Multimodal Large Language Models (MLLMs), yet the underlying principles remain poorly understood. In this paper, we investigate which components of MLLMs contribute to object hallucinations. To analyze image representations while completely avoiding the influence of all other factors other than the image representation itself, we propose a parametric-free representation alignment metric (Pfram) that can measure the similarities between any two representation systems without requiring additional training parameters. Notably, Pfram can also assess the alignment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01151","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/2409.01151/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.01151","created_at":"2026-07-05T09:01:59.694902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01151v1","created_at":"2026-07-05T09:01:59.694902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01151","created_at":"2026-07-05T09:01:59.694902+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YT3CTJTDHJG","created_at":"2026-07-05T09:01:59.694902+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YT3CTJTDHJGHI5T","created_at":"2026-07-05T09:01:59.694902+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YT3CTJT","created_at":"2026-07-05T09:01:59.694902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B","json":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B.json","graph_json":"https://pith.science/api/pith-number/6YT3CTJTDHJGHI5TZM2NHASE6B/graph.json","events_json":"https://pith.science/api/pith-number/6YT3CTJTDHJGHI5TZM2NHASE6B/events.json","paper":"https://pith.science/paper/6YT3CTJT"},"agent_actions":{"view_html":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B","download_json":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B.json","view_paper":"https://pith.science/paper/6YT3CTJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01151&json=true","fetch_graph":"https://pith.science/api/pith-number/6YT3CTJTDHJGHI5TZM2NHASE6B/graph.json","fetch_events":"https://pith.science/api/pith-number/6YT3CTJTDHJGHI5TZM2NHASE6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B/action/storage_attestation","attest_author":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B/action/author_attestation","sign_citation":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B/action/citation_signature","submit_replication":"https://pith.science/pith/6YT3CTJTDHJGHI5TZM2NHASE6B/action/replication_record"}},"created_at":"2026-07-05T09:01:59.694902+00:00","updated_at":"2026-07-05T09:01:59.694902+00:00"}