{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UAP2TLLQDINGFHDJER7DF5E334","short_pith_number":"pith:UAP2TLLQ","canonical_record":{"source":{"id":"2507.15652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T14:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"1bca256b9c6ef18ce5d0955170b6947c23c8062f5827eb26dd093eab8d2f0930","abstract_canon_sha256":"2311d1fa447260539cc3a423f6caeb3f6134b4cd449b12af755854f4a98a518e"},"schema_version":"1.0"},"canonical_sha256":"a01fa9ad701a1a629c69247e32f49bdf23f9d0df08e9b118c95f97cef23cad25","source":{"kind":"arxiv","id":"2507.15652","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15652","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15652v1","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15652","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"UAP2TLLQDING","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"pith_short_16","alias_value":"UAP2TLLQDINGFHDJ","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"pith_short_8","alias_value":"UAP2TLLQ","created_at":"2026-07-05T11:40:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UAP2TLLQDINGFHDJER7DF5E334","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T14:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"1bca256b9c6ef18ce5d0955170b6947c23c8062f5827eb26dd093eab8d2f0930","abstract_canon_sha256":"2311d1fa447260539cc3a423f6caeb3f6134b4cd449b12af755854f4a98a518e"},"schema_version":"1.0"},"canonical_sha256":"a01fa9ad701a1a629c69247e32f49bdf23f9d0df08e9b118c95f97cef23cad25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:41.379995Z","signature_b64":"B6GLMoUMFk7c+Q9KEOZIGNGQbXgDe0miAb/rwp/EkYRXPNv7DsyZ9TbgFhrdLXL9rRWph67+rJsXnCXhGPK6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a01fa9ad701a1a629c69247e32f49bdf23f9d0df08e9b118c95f97cef23cad25","last_reissued_at":"2026-07-05T11:40:41.379537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:41.379537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15652","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ch0cHUCWyv9H0rBqHiQ/3Q9omLrl/bCZRiBiYvyx4Mf8l0HqLRlxQ64jUup04sTEVIzswJ0Fl3aSlHmSt0RUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:32.159113Z"},"content_sha256":"3ae29d17b1abe63bf63cfa61585f52c2a76fd2820c04f9becb38d7f322118845","schema_version":"1.0","event_id":"sha256:3ae29d17b1abe63bf63cfa61585f52c2a76fd2820c04f9becb38d7f322118845"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UAP2TLLQDINGFHDJER7DF5E334","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Visual Facts from Intermediate Layers for Mitigating Hallucinations in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Chen, Haoran Zhou, Zihan Zhang","submitted_at":"2025-07-21T14:15:34Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have made significant strides by combining visual recognition and language understanding to generate content that is both coherent and contextually accurate. However, MLLMs continue to struggle with object hallucinations, where models produce seemingly plausible but factually incorrect outputs, including objects that do not exist in the image. Recent work has revealed that the prior knowledge in MLLMs significantly suppresses visual information in deep layers, causing hallucinatory outputs. However, how these priors suppress visual information at the in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15652","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/2507.15652/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":"2026-07-05T11:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYete/p1UfpgST+Vrb2aNRPaJSDJmUeAKAoYIVVEyWB0dqZpaVPQdCNCwk1Yza5YuGk9qE1SQIqPk/kkmta2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:32.159508Z"},"content_sha256":"3db629a4a33cab99137914d3985b9323afe5a7d2f8e7a7b69a135f3745cbc01f","schema_version":"1.0","event_id":"sha256:3db629a4a33cab99137914d3985b9323afe5a7d2f8e7a7b69a135f3745cbc01f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAP2TLLQDINGFHDJER7DF5E334/bundle.json","state_url":"https://pith.science/pith/UAP2TLLQDINGFHDJER7DF5E334/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAP2TLLQDINGFHDJER7DF5E334/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":"2026-07-09T01:03:32Z","links":{"resolver":"https://pith.science/pith/UAP2TLLQDINGFHDJER7DF5E334","bundle":"https://pith.science/pith/UAP2TLLQDINGFHDJER7DF5E334/bundle.json","state":"https://pith.science/pith/UAP2TLLQDINGFHDJER7DF5E334/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAP2TLLQDINGFHDJER7DF5E334/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UAP2TLLQDINGFHDJER7DF5E334","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":"2311d1fa447260539cc3a423f6caeb3f6134b4cd449b12af755854f4a98a518e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T14:15:34Z","title_canon_sha256":"1bca256b9c6ef18ce5d0955170b6947c23c8062f5827eb26dd093eab8d2f0930"},"schema_version":"1.0","source":{"id":"2507.15652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15652","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15652v1","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15652","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"UAP2TLLQDING","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"pith_short_16","alias_value":"UAP2TLLQDINGFHDJ","created_at":"2026-07-05T11:40:41Z"},{"alias_kind":"pith_short_8","alias_value":"UAP2TLLQ","created_at":"2026-07-05T11:40:41Z"}],"graph_snapshots":[{"event_id":"sha256:3db629a4a33cab99137914d3985b9323afe5a7d2f8e7a7b69a135f3745cbc01f","target":"graph","created_at":"2026-07-05T11:40:41Z","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/2507.15652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have made significant strides by combining visual recognition and language understanding to generate content that is both coherent and contextually accurate. However, MLLMs continue to struggle with object hallucinations, where models produce seemingly plausible but factually incorrect outputs, including objects that do not exist in the image. Recent work has revealed that the prior knowledge in MLLMs significantly suppresses visual information in deep layers, causing hallucinatory outputs. However, how these priors suppress visual information at the in","authors_text":"Hao Chen, Haoran Zhou, Zihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T14:15:34Z","title":"Extracting Visual Facts from Intermediate Layers for Mitigating Hallucinations in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15652","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":"sha256:3ae29d17b1abe63bf63cfa61585f52c2a76fd2820c04f9becb38d7f322118845","target":"record","created_at":"2026-07-05T11:40:41Z","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":"2311d1fa447260539cc3a423f6caeb3f6134b4cd449b12af755854f4a98a518e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T14:15:34Z","title_canon_sha256":"1bca256b9c6ef18ce5d0955170b6947c23c8062f5827eb26dd093eab8d2f0930"},"schema_version":"1.0","source":{"id":"2507.15652","kind":"arxiv","version":1}},"canonical_sha256":"a01fa9ad701a1a629c69247e32f49bdf23f9d0df08e9b118c95f97cef23cad25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a01fa9ad701a1a629c69247e32f49bdf23f9d0df08e9b118c95f97cef23cad25","first_computed_at":"2026-07-05T11:40:41.379537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:41.379537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B6GLMoUMFk7c+Q9KEOZIGNGQbXgDe0miAb/rwp/EkYRXPNv7DsyZ9TbgFhrdLXL9rRWph67+rJsXnCXhGPK6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:41.379995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ae29d17b1abe63bf63cfa61585f52c2a76fd2820c04f9becb38d7f322118845","sha256:3db629a4a33cab99137914d3985b9323afe5a7d2f8e7a7b69a135f3745cbc01f"],"state_sha256":"20320fae2379fb413f4b53de79e826aced4e1db77ce335b92f014f09d8895f9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UfNmnyXbjCilZSyfTBu2e/LPH4Z6dadZ8yiYOYDzM5YT2fyOoKyp00Izfq4LePXh5+mF9rOWWoNWRBwfpM6cCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:03:32.161644Z","bundle_sha256":"2d2dca39087fcded5d40537977517652d4cede4c9a5c733be1721b741e79632e"}}