{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HYNXX2D3BBZ7N5IJCMATS754SI","short_pith_number":"pith:HYNXX2D3","canonical_record":{"source":{"id":"2407.21771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T17:46:57Z","cross_cats_sorted":[],"title_canon_sha256":"8a823ed20d3b9ff79b6e55191fd42bba4c869c136e360d7e0cf93ca41e964f99","abstract_canon_sha256":"538ad52543425a342aea7fdc4f86d538aa93c8a656dcaa6d767690e9898c9336"},"schema_version":"1.0"},"canonical_sha256":"3e1b7be87b0873f6f5091301397fbc920ab580a687ad87eefc3752388a619a12","source":{"kind":"arxiv","id":"2407.21771","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21771","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21771v1","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21771","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"pith_short_12","alias_value":"HYNXX2D3BBZ7","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"pith_short_16","alias_value":"HYNXX2D3BBZ7N5IJ","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"pith_short_8","alias_value":"HYNXX2D3","created_at":"2026-07-05T08:50:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HYNXX2D3BBZ7N5IJCMATS754SI","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T17:46:57Z","cross_cats_sorted":[],"title_canon_sha256":"8a823ed20d3b9ff79b6e55191fd42bba4c869c136e360d7e0cf93ca41e964f99","abstract_canon_sha256":"538ad52543425a342aea7fdc4f86d538aa93c8a656dcaa6d767690e9898c9336"},"schema_version":"1.0"},"canonical_sha256":"3e1b7be87b0873f6f5091301397fbc920ab580a687ad87eefc3752388a619a12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:43.379911Z","signature_b64":"dbL2GKlXRlQy55noYrMNoidjF1cmmY7IPduUXGOOUH6hokXsAwSfaDc9JjicvmoK/svzCtPBCuQk9h0jKATlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e1b7be87b0873f6f5091301397fbc920ab580a687ad87eefc3752388a619a12","last_reissued_at":"2026-07-05T08:50:43.379569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:43.379569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21771","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":"2026-07-05T08:50:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1agGrvLWG8uSJyYeGpElhqHTOFajqD8ipUg+0bt0iNtMDRMCWLxATZzo+0lUS8NlzIa+2r23jSzcBncKB2KpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:33:54.431775Z"},"content_sha256":"6e4d95ff089b8349177c80dc02f0d8ee9f34dfdc240f9e00a33bf11d4fbe811e","schema_version":"1.0","event_id":"sha256:6e4d95ff089b8349177c80dc02f0d8ee9f34dfdc240f9e00a33bf11d4fbe811e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HYNXX2D3BBZ7N5IJCMATS754SI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kecheng Zheng, Shi Liu, Wei Chen","submitted_at":"2024-07-31T17:46:57Z","abstract_excerpt":"Existing Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. However, the scale disparity between vision encoder and language model may led to LLMs assuming a predominant role in multi-modal comprehension. This imbalance in LVLMs may result in the instances of hallucinatory. Concretely, LVLMs may generate consistent descriptions with or without visual input, indicating that certain outputs are influenced solely by context text. We refer to this phenomenon as \"text inerti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21771","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/2407.21771/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":"2026-07-05T08:50:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zohgMfzuDYLxBwxtLWuwOt6yYOOAL4OA+Zb5TYLeFNcgNN4v29VYGOKAJBx0AMk6P1lPfS0P0/Z8BsCWXcAGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:33:54.432129Z"},"content_sha256":"1b95bca8045b48d2ffd66caf9dc3a5d3e46f6fab4202d37355dec58d31dabef7","schema_version":"1.0","event_id":"sha256:1b95bca8045b48d2ffd66caf9dc3a5d3e46f6fab4202d37355dec58d31dabef7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/bundle.json","state_url":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYNXX2D3BBZ7N5IJCMATS754SI/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":"2026-07-07T12:33:54Z","links":{"resolver":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI","bundle":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/bundle.json","state":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYNXX2D3BBZ7N5IJCMATS754SI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HYNXX2D3BBZ7N5IJCMATS754SI","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":"538ad52543425a342aea7fdc4f86d538aa93c8a656dcaa6d767690e9898c9336","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T17:46:57Z","title_canon_sha256":"8a823ed20d3b9ff79b6e55191fd42bba4c869c136e360d7e0cf93ca41e964f99"},"schema_version":"1.0","source":{"id":"2407.21771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21771","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21771v1","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21771","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"pith_short_12","alias_value":"HYNXX2D3BBZ7","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"pith_short_16","alias_value":"HYNXX2D3BBZ7N5IJ","created_at":"2026-07-05T08:50:43Z"},{"alias_kind":"pith_short_8","alias_value":"HYNXX2D3","created_at":"2026-07-05T08:50:43Z"}],"graph_snapshots":[{"event_id":"sha256:1b95bca8045b48d2ffd66caf9dc3a5d3e46f6fab4202d37355dec58d31dabef7","target":"graph","created_at":"2026-07-05T08:50:43Z","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/2407.21771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. However, the scale disparity between vision encoder and language model may led to LLMs assuming a predominant role in multi-modal comprehension. This imbalance in LVLMs may result in the instances of hallucinatory. Concretely, LVLMs may generate consistent descriptions with or without visual input, indicating that certain outputs are influenced solely by context text. We refer to this phenomenon as \"text inerti","authors_text":"Kecheng Zheng, Shi Liu, Wei Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T17:46:57Z","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21771","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":"sha256:6e4d95ff089b8349177c80dc02f0d8ee9f34dfdc240f9e00a33bf11d4fbe811e","target":"record","created_at":"2026-07-05T08:50:43Z","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":"538ad52543425a342aea7fdc4f86d538aa93c8a656dcaa6d767690e9898c9336","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T17:46:57Z","title_canon_sha256":"8a823ed20d3b9ff79b6e55191fd42bba4c869c136e360d7e0cf93ca41e964f99"},"schema_version":"1.0","source":{"id":"2407.21771","kind":"arxiv","version":1}},"canonical_sha256":"3e1b7be87b0873f6f5091301397fbc920ab580a687ad87eefc3752388a619a12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e1b7be87b0873f6f5091301397fbc920ab580a687ad87eefc3752388a619a12","first_computed_at":"2026-07-05T08:50:43.379569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:43.379569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dbL2GKlXRlQy55noYrMNoidjF1cmmY7IPduUXGOOUH6hokXsAwSfaDc9JjicvmoK/svzCtPBCuQk9h0jKATlDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:43.379911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e4d95ff089b8349177c80dc02f0d8ee9f34dfdc240f9e00a33bf11d4fbe811e","sha256:1b95bca8045b48d2ffd66caf9dc3a5d3e46f6fab4202d37355dec58d31dabef7"],"state_sha256":"1c1a583cbdf92f200fa5ece45ae9cd523f43f79f0f9db4434e962aa60a402d88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+CaF2X8DiOoVp9lOGl8C72965jHdXfx0KyhtyDJ4JznwnVRc+7214Vm7xU3dyE824mhJ9IbWDI/jq77N/w8ABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:33:54.433991Z","bundle_sha256":"7eb9edcb1a3ef9346d2109173da2c40a8e876be2bad3aba904a19b4817492ec3"}}