{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R24PPKZ5T7XMD642ZIA7OMLVYY","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":"a9ce105960cab0257ba50a2a1696155cc7a9bb181dfa678711f72e5af4a4df27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T05:11:46Z","title_canon_sha256":"0e82280c54cfd192c6aae9c52a83bc6cfaa7497adaa69293f69ee97a4f90aa91"},"schema_version":"1.0","source":{"id":"2506.17901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17901","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17901v1","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17901","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_12","alias_value":"R24PPKZ5T7XM","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_16","alias_value":"R24PPKZ5T7XMD642","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_8","alias_value":"R24PPKZ5","created_at":"2026-07-05T11:25:25Z"}],"graph_snapshots":[{"event_id":"sha256:7d3f4dd3e82f837cc37427146003f73714faa18c2b2fe79e2295ca81277c0ec8","target":"graph","created_at":"2026-07-05T11:25:25Z","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/2506.17901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) excel in vision-language tasks, such as image captioning and visual question answering. However, they often suffer from over-reliance on spurious correlations, primarily due to linguistic priors that distract the model from leveraging actual visual information. To address these issues, we introduce MMGrounded-PostAlign, a post-multimodal alignment framework designed to enhance the visual understanding capabilities and mitigate the hallucinations of MLLMs. Our framework incorporates a multimodal grounding module for both visual grounding, which identifie","authors_text":"Jian Wu, Jindong Gu, Philip Torr, Yang Zhang, Yixuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T05:11:46Z","title":"PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17901","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:c0e973e2061a3e3c918f4b3adfd94bf79bd11ca72fd6b76185836bf38f795e99","target":"record","created_at":"2026-07-05T11:25:25Z","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":"a9ce105960cab0257ba50a2a1696155cc7a9bb181dfa678711f72e5af4a4df27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T05:11:46Z","title_canon_sha256":"0e82280c54cfd192c6aae9c52a83bc6cfaa7497adaa69293f69ee97a4f90aa91"},"schema_version":"1.0","source":{"id":"2506.17901","kind":"arxiv","version":1}},"canonical_sha256":"8eb8f7ab3d9feec1fb9aca01f73175c60ef562b03e77b1bfe8c10edabfc2e360","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eb8f7ab3d9feec1fb9aca01f73175c60ef562b03e77b1bfe8c10edabfc2e360","first_computed_at":"2026-07-05T11:25:25.156593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:25.156593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IRVLG2fUKpsmcH0OCoi7Bv3LYQYDk1cIPJcWquKrdujG2meq63EWIBsJ0SmhS0f5I45/EG0dQqBbRXuPJGoPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:25.156995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0e973e2061a3e3c918f4b3adfd94bf79bd11ca72fd6b76185836bf38f795e99","sha256:7d3f4dd3e82f837cc37427146003f73714faa18c2b2fe79e2295ca81277c0ec8"],"state_sha256":"bd6d96367bf715884d175387422edb992be2699581a597b52c8b24c4f5614242"}