{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FZRR5JX5PSO3D7XNE3UDWVJFZ6","short_pith_number":"pith:FZRR5JX5","schema_version":"1.0","canonical_sha256":"2e631ea6fd7c9db1feed26e83b5525cfb973c9a763d8ccaed223edfecaa597c6","source":{"kind":"arxiv","id":"2507.07731","version":1},"attestation_state":"computed","paper":{"title":"Energy-Guided Decoding for Object Hallucination Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailin Deng, Christopher Zach, Xixi Liu","submitted_at":"2025-07-10T13:12:08Z","abstract_excerpt":"Mitigating object hallucination in large vision-language models (LVLMs) is critical to their safe deployment. Existing methods either are restricted to specific decoding methods, or demand sophisticated modifications to visual inputs, or rely on knowledge from external models. In this work, we first reveal the phenomenon that VLMs exhibit significant imbalance in the ``Yes'' ratio ( \\ie, the fraction of ``Yes'' answers among the total number of questions) across three different visual question answering (VQA) datasets. Furthermore, we propose an energy-based decoding method, which dynamically "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.07731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T13:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"949e581d7c88a518770c14165adab72ff6201ad45a427d4c486a1cea58574a11","abstract_canon_sha256":"fc1f0e15c7d5cf9bf42e4456cb0be8bfcf7de354d6c81b1fb12904e4c0d36333"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:04.158048Z","signature_b64":"QtD55sv2evHY9xT7If53WikK50zUDvzNjjpkuEJ2q723tNz4URiNFpPGsT+TqhRWs6dtl1tTWeDRdb+xfyAoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e631ea6fd7c9db1feed26e83b5525cfb973c9a763d8ccaed223edfecaa597c6","last_reissued_at":"2026-07-05T11:35:04.157600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:04.157600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Guided Decoding for Object Hallucination Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailin Deng, Christopher Zach, Xixi Liu","submitted_at":"2025-07-10T13:12:08Z","abstract_excerpt":"Mitigating object hallucination in large vision-language models (LVLMs) is critical to their safe deployment. Existing methods either are restricted to specific decoding methods, or demand sophisticated modifications to visual inputs, or rely on knowledge from external models. In this work, we first reveal the phenomenon that VLMs exhibit significant imbalance in the ``Yes'' ratio ( \\ie, the fraction of ``Yes'' answers among the total number of questions) across three different visual question answering (VQA) datasets. Furthermore, we propose an energy-based decoding method, which dynamically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07731","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/2507.07731/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.07731","created_at":"2026-07-05T11:35:04.157657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07731v1","created_at":"2026-07-05T11:35:04.157657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07731","created_at":"2026-07-05T11:35:04.157657+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZRR5JX5PSO3","created_at":"2026-07-05T11:35:04.157657+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZRR5JX5PSO3D7XN","created_at":"2026-07-05T11:35:04.157657+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZRR5JX5","created_at":"2026-07-05T11:35:04.157657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6","json":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6.json","graph_json":"https://pith.science/api/pith-number/FZRR5JX5PSO3D7XNE3UDWVJFZ6/graph.json","events_json":"https://pith.science/api/pith-number/FZRR5JX5PSO3D7XNE3UDWVJFZ6/events.json","paper":"https://pith.science/paper/FZRR5JX5"},"agent_actions":{"view_html":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6","download_json":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6.json","view_paper":"https://pith.science/paper/FZRR5JX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07731&json=true","fetch_graph":"https://pith.science/api/pith-number/FZRR5JX5PSO3D7XNE3UDWVJFZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/FZRR5JX5PSO3D7XNE3UDWVJFZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6/action/storage_attestation","attest_author":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6/action/author_attestation","sign_citation":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6/action/citation_signature","submit_replication":"https://pith.science/pith/FZRR5JX5PSO3D7XNE3UDWVJFZ6/action/replication_record"}},"created_at":"2026-07-05T11:35:04.157657+00:00","updated_at":"2026-07-05T11:35:04.157657+00:00"}