{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WSOBN6Y7FTVWKPTZPC6IJ3SVG2","short_pith_number":"pith:WSOBN6Y7","canonical_record":{"source":{"id":"2508.01678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-03T09:11:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba89fdb55f0a8fe03924f12f33a44d60aa696e51de2d700fb6007f708d08d197","abstract_canon_sha256":"cdfd2bfac2c396b7618822186a4e6f2a963f4f442fb5b5b457ff17a13ffd4452"},"schema_version":"1.0"},"canonical_sha256":"b49c16fb1f2ceb653e7978bc84ee55369fcf4c507efdbeb494a88179d1a3393e","source":{"kind":"arxiv","id":"2508.01678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01678","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01678v1","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01678","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"pith_short_12","alias_value":"WSOBN6Y7FTVW","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"pith_short_16","alias_value":"WSOBN6Y7FTVWKPTZ","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"pith_short_8","alias_value":"WSOBN6Y7","created_at":"2026-07-05T11:47:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WSOBN6Y7FTVWKPTZPC6IJ3SVG2","target":"record","payload":{"canonical_record":{"source":{"id":"2508.01678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-03T09:11:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba89fdb55f0a8fe03924f12f33a44d60aa696e51de2d700fb6007f708d08d197","abstract_canon_sha256":"cdfd2bfac2c396b7618822186a4e6f2a963f4f442fb5b5b457ff17a13ffd4452"},"schema_version":"1.0"},"canonical_sha256":"b49c16fb1f2ceb653e7978bc84ee55369fcf4c507efdbeb494a88179d1a3393e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:43.739441Z","signature_b64":"u//NimISkqOdL0R8n6KfHSS4G1hS9tRMcfKLov93Wj9/V7au+UjSO7vqkjmxKdLeX3PnafE//L9fhMWA4msBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b49c16fb1f2ceb653e7978bc84ee55369fcf4c507efdbeb494a88179d1a3393e","last_reissued_at":"2026-07-05T11:47:43.738953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:43.738953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.01678","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":"2026-07-05T11:47:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZXtS7Q0Sxul/1Kn1MjGavB8AZwvqawU8FwNwnEv6Wv/3c7qvMFhZntlFfW+RIfjQxne4qx+ECZ0P6u0f1p0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:28:45.239766Z"},"content_sha256":"a3e23578d557c998a4df9cb85249f1e7f45c4d618415774d87d1fe6c186bc9ea","schema_version":"1.0","event_id":"sha256:a3e23578d557c998a4df9cb85249f1e7f45c4d618415774d87d1fe6c186bc9ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WSOBN6Y7FTVWKPTZPC6IJ3SVG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Yiwei Wang, Yujun Cai, Zhaochen Wang","submitted_at":"2025-08-03T09:11:18Z","abstract_excerpt":"Vision-Language Models (VLMs) often suffer from hallucination, partly due to challenges in aligning multimodal information. We propose Prompt-in-Image, a simple method that embeds textual instructions directly into images. This removes the need for separate text inputs and forces the model to process all content through the visual channel. We evaluate this method on three popular open-source VLMs: Qwen2.5-VL, LLaVA-1.5, and InstructBLIP. The results reveal sharp differences. Prompt-in-Image improves Qwen2.5-VL's performance, increasing POPE accuracy by 4.1 percent (from 80.2 percent to 84.3 pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01678","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/2508.01678/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":"2026-07-05T11:47:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUQrmPunMQeF0e/gixJxRoPcz6yshVU6SffDRtXW/EOQzw6nKbxrdV5f3dXxrp3PTysGLI6L1Ez2rcbaPXhgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:28:45.241177Z"},"content_sha256":"c16bd24e5f5354f7e0895c4baa308b42fa380bf7dafaa875fbaf1e704e3bf48f","schema_version":"1.0","event_id":"sha256:c16bd24e5f5354f7e0895c4baa308b42fa380bf7dafaa875fbaf1e704e3bf48f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSOBN6Y7FTVWKPTZPC6IJ3SVG2/bundle.json","state_url":"https://pith.science/pith/WSOBN6Y7FTVWKPTZPC6IJ3SVG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSOBN6Y7FTVWKPTZPC6IJ3SVG2/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":"2026-08-11T01:28:45Z","links":{"resolver":"https://pith.science/pith/WSOBN6Y7FTVWKPTZPC6IJ3SVG2","bundle":"https://pith.science/pith/WSOBN6Y7FTVWKPTZPC6IJ3SVG2/bundle.json","state":"https://pith.science/pith/WSOBN6Y7FTVWKPTZPC6IJ3SVG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSOBN6Y7FTVWKPTZPC6IJ3SVG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WSOBN6Y7FTVWKPTZPC6IJ3SVG2","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":"cdfd2bfac2c396b7618822186a4e6f2a963f4f442fb5b5b457ff17a13ffd4452","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-03T09:11:18Z","title_canon_sha256":"ba89fdb55f0a8fe03924f12f33a44d60aa696e51de2d700fb6007f708d08d197"},"schema_version":"1.0","source":{"id":"2508.01678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01678","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01678v1","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01678","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"pith_short_12","alias_value":"WSOBN6Y7FTVW","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"pith_short_16","alias_value":"WSOBN6Y7FTVWKPTZ","created_at":"2026-07-05T11:47:43Z"},{"alias_kind":"pith_short_8","alias_value":"WSOBN6Y7","created_at":"2026-07-05T11:47:43Z"}],"graph_snapshots":[{"event_id":"sha256:c16bd24e5f5354f7e0895c4baa308b42fa380bf7dafaa875fbaf1e704e3bf48f","target":"graph","created_at":"2026-07-05T11:47:43Z","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/2508.01678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) often suffer from hallucination, partly due to challenges in aligning multimodal information. We propose Prompt-in-Image, a simple method that embeds textual instructions directly into images. This removes the need for separate text inputs and forces the model to process all content through the visual channel. We evaluate this method on three popular open-source VLMs: Qwen2.5-VL, LLaVA-1.5, and InstructBLIP. The results reveal sharp differences. Prompt-in-Image improves Qwen2.5-VL's performance, increasing POPE accuracy by 4.1 percent (from 80.2 percent to 84.3 pe","authors_text":"Yiwei Wang, Yujun Cai, Zhaochen Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-03T09:11:18Z","title":"Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01678","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:a3e23578d557c998a4df9cb85249f1e7f45c4d618415774d87d1fe6c186bc9ea","target":"record","created_at":"2026-07-05T11:47:43Z","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":"cdfd2bfac2c396b7618822186a4e6f2a963f4f442fb5b5b457ff17a13ffd4452","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-03T09:11:18Z","title_canon_sha256":"ba89fdb55f0a8fe03924f12f33a44d60aa696e51de2d700fb6007f708d08d197"},"schema_version":"1.0","source":{"id":"2508.01678","kind":"arxiv","version":1}},"canonical_sha256":"b49c16fb1f2ceb653e7978bc84ee55369fcf4c507efdbeb494a88179d1a3393e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b49c16fb1f2ceb653e7978bc84ee55369fcf4c507efdbeb494a88179d1a3393e","first_computed_at":"2026-07-05T11:47:43.738953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:43.738953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u//NimISkqOdL0R8n6KfHSS4G1hS9tRMcfKLov93Wj9/V7au+UjSO7vqkjmxKdLeX3PnafE//L9fhMWA4msBAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:43.739441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3e23578d557c998a4df9cb85249f1e7f45c4d618415774d87d1fe6c186bc9ea","sha256:c16bd24e5f5354f7e0895c4baa308b42fa380bf7dafaa875fbaf1e704e3bf48f"],"state_sha256":"fe1f7748f0436f49cf47c831a99a08b9e6ecdae6a16e01af20240967da8a612e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sys8T8VzStQbx7uRqHADzi3oEvuL13mW2e4AxCLIl/ZHnyviJLBub9WqNYcJ/SRW3JP9xNuxivERMFow5YIQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:28:45.250179Z","bundle_sha256":"93224343e04a0d14cb950ab880195a5f2de5590e6d70bd4898f07a6560065f3a"}}