{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BOVAFVCJT4CHXAVEJ7X5XVEZTP","short_pith_number":"pith:BOVAFVCJ","canonical_record":{"source":{"id":"2510.22067","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-24T23:04:26Z","cross_cats_sorted":[],"title_canon_sha256":"3ef416909dd1928b262e2e6e3eb0db2252e81a0fa208eb24dc329e178e59b8b1","abstract_canon_sha256":"3c63e93e96c8eb8b6e36ba07e58bc0b9dc5e2a56c42883bb8775ef56b25201c9"},"schema_version":"1.0"},"canonical_sha256":"0baa02d4499f047b82a44fefdbd4999bd8c64e85b5a466709012cffceabe4a0b","source":{"kind":"arxiv","id":"2510.22067","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.22067","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2510.22067v3","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.22067","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"BOVAFVCJT4CH","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"BOVAFVCJT4CHXAVE","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"BOVAFVCJ","created_at":"2026-06-01T02:03:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BOVAFVCJT4CHXAVEJ7X5XVEZTP","target":"record","payload":{"canonical_record":{"source":{"id":"2510.22067","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-24T23:04:26Z","cross_cats_sorted":[],"title_canon_sha256":"3ef416909dd1928b262e2e6e3eb0db2252e81a0fa208eb24dc329e178e59b8b1","abstract_canon_sha256":"3c63e93e96c8eb8b6e36ba07e58bc0b9dc5e2a56c42883bb8775ef56b25201c9"},"schema_version":"1.0"},"canonical_sha256":"0baa02d4499f047b82a44fefdbd4999bd8c64e85b5a466709012cffceabe4a0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:28.963296Z","signature_b64":"qH+3giFMa3lNWoLgKyVk01m7B5W3IydGKO0Tm4ODE3CrzZQ9Ldh8c86VvaLTwVRnJ7zR2sXcCjxAIBcGN+ibCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0baa02d4499f047b82a44fefdbd4999bd8c64e85b5a466709012cffceabe4a0b","last_reissued_at":"2026-06-01T02:03:28.962171Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:28.962171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.22067","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T02:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybHJ84zEEsKTapVHAqaToJoUz4UjMBkqAPtWBVLAHhiaYTY7Ttlx9Dcml64igShzw6k2p1P6/mAg9yzeKrJeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T15:11:37.555013Z"},"content_sha256":"94beefc8814768d3fb382460522788e43b3837fd316caf9756875fc5f30af2f8","schema_version":"1.0","event_id":"sha256:94beefc8814768d3fb382460522788e43b3837fd316caf9756875fc5f30af2f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BOVAFVCJT4CHXAVEJ7X5XVEZTP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Shang, Evangelia Spiliopoulou, Nikolaos Pappas, Zheng Qi","submitted_at":"2025-10-24T23:04:26Z","abstract_excerpt":"Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowledge rather than visual inputs. Some methods attempt to mitigate hallucination by amplifying visual token attention proportionally to their attention scores. However, these methods overlook the visual attention sink problem, where attention is frequently misallocated to task-irrelevant visual regions, and neglect cross-modal fusion balance by enhancing only visual attention witho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.22067","kind":"arxiv","version":3},"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/2510.22067/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":"2026-06-01T02:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5CAyi/7ANvXz5el9gJm58ZR9+zuPT7QVf5wRH6LMGLMVyL9mxXB0hwGZCweSxOljXh/LIPVijzB91duJcJ41Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T15:11:37.555480Z"},"content_sha256":"2c04b5f7ea57e17dac957355500261349621542f1fcf02cfb2ea1ed9bd5c8155","schema_version":"1.0","event_id":"sha256:2c04b5f7ea57e17dac957355500261349621542f1fcf02cfb2ea1ed9bd5c8155"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOVAFVCJT4CHXAVEJ7X5XVEZTP/bundle.json","state_url":"https://pith.science/pith/BOVAFVCJT4CHXAVEJ7X5XVEZTP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOVAFVCJT4CHXAVEJ7X5XVEZTP/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":"2026-06-03T15:11:37Z","links":{"resolver":"https://pith.science/pith/BOVAFVCJT4CHXAVEJ7X5XVEZTP","bundle":"https://pith.science/pith/BOVAFVCJT4CHXAVEJ7X5XVEZTP/bundle.json","state":"https://pith.science/pith/BOVAFVCJT4CHXAVEJ7X5XVEZTP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOVAFVCJT4CHXAVEJ7X5XVEZTP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BOVAFVCJT4CHXAVEJ7X5XVEZTP","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":"3c63e93e96c8eb8b6e36ba07e58bc0b9dc5e2a56c42883bb8775ef56b25201c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-24T23:04:26Z","title_canon_sha256":"3ef416909dd1928b262e2e6e3eb0db2252e81a0fa208eb24dc329e178e59b8b1"},"schema_version":"1.0","source":{"id":"2510.22067","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.22067","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2510.22067v3","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.22067","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"BOVAFVCJT4CH","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"BOVAFVCJT4CHXAVE","created_at":"2026-06-01T02:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"BOVAFVCJ","created_at":"2026-06-01T02:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:2c04b5f7ea57e17dac957355500261349621542f1fcf02cfb2ea1ed9bd5c8155","target":"graph","created_at":"2026-06-01T02:03:28Z","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/2510.22067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowledge rather than visual inputs. Some methods attempt to mitigate hallucination by amplifying visual token attention proportionally to their attention scores. However, these methods overlook the visual attention sink problem, where attention is frequently misallocated to task-irrelevant visual regions, and neglect cross-modal fusion balance by enhancing only visual attention witho","authors_text":"Chao Shang, Evangelia Spiliopoulou, Nikolaos Pappas, Zheng Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-24T23:04:26Z","title":"Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.22067","kind":"arxiv","version":3},"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":"sha256:94beefc8814768d3fb382460522788e43b3837fd316caf9756875fc5f30af2f8","target":"record","created_at":"2026-06-01T02:03:28Z","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":"3c63e93e96c8eb8b6e36ba07e58bc0b9dc5e2a56c42883bb8775ef56b25201c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-24T23:04:26Z","title_canon_sha256":"3ef416909dd1928b262e2e6e3eb0db2252e81a0fa208eb24dc329e178e59b8b1"},"schema_version":"1.0","source":{"id":"2510.22067","kind":"arxiv","version":3}},"canonical_sha256":"0baa02d4499f047b82a44fefdbd4999bd8c64e85b5a466709012cffceabe4a0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0baa02d4499f047b82a44fefdbd4999bd8c64e85b5a466709012cffceabe4a0b","first_computed_at":"2026-06-01T02:03:28.962171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:03:28.962171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qH+3giFMa3lNWoLgKyVk01m7B5W3IydGKO0Tm4ODE3CrzZQ9Ldh8c86VvaLTwVRnJ7zR2sXcCjxAIBcGN+ibCQ==","signature_status":"signed_v1","signed_at":"2026-06-01T02:03:28.963296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.22067","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94beefc8814768d3fb382460522788e43b3837fd316caf9756875fc5f30af2f8","sha256:2c04b5f7ea57e17dac957355500261349621542f1fcf02cfb2ea1ed9bd5c8155"],"state_sha256":"d495e4d40461b43eb3e9a775ac64b3234844843f07a23ff593db35ea6335e7fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RvDYiY/VDWJT5qtC5uff3EhIpRn1ySDIZhtuKrbRemgeCe8FEzhsi4VRIGvSE8VE1kwtWnc4CEs6zB4qYe16Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T15:11:37.557478Z","bundle_sha256":"a4258d7318e9dc319ac004f4387d39d682ce7519f62acbc06455aa160794b9ab"}}