{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5CYBEHPN6SIZWHUN6YNVIR4UGD","short_pith_number":"pith:5CYBEHPN","schema_version":"1.0","canonical_sha256":"e8b0121dedf4919b1e8df61b54479430dbb61f1c1f0df27f7335aba897ee4607","source":{"kind":"arxiv","id":"2411.12713","version":1},"attestation_state":"computed","paper":{"title":"CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Dongmei Jiang, Junyuan Xiao, Qingmin Liao, Wenming Yang, Xu Li, Yaowei Wang, Yapeng Tian, Zhehan Kan, Zihan Liao","submitted_at":"2024-11-19T18:27:31Z","abstract_excerpt":"Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and autonomous systems. Despite previous efforts to mitigate hallucinations, a persistent issue remains: visual defect from vision-language misalignment, creating a bottleneck in visual processing capacity. To address this challenge, we develop Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs (CATCH), based on the Informa"},"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":"2411.12713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-19T18:27:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5687fb5b9d6e19826e000212596560ab454f0dc7b1a0256b53fd86f4d8ad0e01","abstract_canon_sha256":"924d7a9fb3d4c2de978c945ece087b3fa6b2622065486c0c88c143ea3415ee21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:47.233064Z","signature_b64":"1QnzJN/zi//hvrBHCVI9DIf7T9D+RdgXwgLwpYtWb3z7HBjx7GvQ4myUhvxQhhiX3o2gIsz6ILxB2uNTwf/MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8b0121dedf4919b1e8df61b54479430dbb61f1c1f0df27f7335aba897ee4607","last_reissued_at":"2026-07-05T09:37:47.232297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:47.232297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Dongmei Jiang, Junyuan Xiao, Qingmin Liao, Wenming Yang, Xu Li, Yaowei Wang, Yapeng Tian, Zhehan Kan, Zihan Liao","submitted_at":"2024-11-19T18:27:31Z","abstract_excerpt":"Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and autonomous systems. Despite previous efforts to mitigate hallucinations, a persistent issue remains: visual defect from vision-language misalignment, creating a bottleneck in visual processing capacity. To address this challenge, we develop Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs (CATCH), based on the Informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12713","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/2411.12713/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":"2411.12713","created_at":"2026-07-05T09:37:47.232366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12713v1","created_at":"2026-07-05T09:37:47.232366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12713","created_at":"2026-07-05T09:37:47.232366+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CYBEHPN6SIZ","created_at":"2026-07-05T09:37:47.232366+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CYBEHPN6SIZWHUN","created_at":"2026-07-05T09:37:47.232366+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CYBEHPN","created_at":"2026-07-05T09:37:47.232366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04641","citing_title":"CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD","json":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD.json","graph_json":"https://pith.science/api/pith-number/5CYBEHPN6SIZWHUN6YNVIR4UGD/graph.json","events_json":"https://pith.science/api/pith-number/5CYBEHPN6SIZWHUN6YNVIR4UGD/events.json","paper":"https://pith.science/paper/5CYBEHPN"},"agent_actions":{"view_html":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD","download_json":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD.json","view_paper":"https://pith.science/paper/5CYBEHPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12713&json=true","fetch_graph":"https://pith.science/api/pith-number/5CYBEHPN6SIZWHUN6YNVIR4UGD/graph.json","fetch_events":"https://pith.science/api/pith-number/5CYBEHPN6SIZWHUN6YNVIR4UGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD/action/storage_attestation","attest_author":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD/action/author_attestation","sign_citation":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD/action/citation_signature","submit_replication":"https://pith.science/pith/5CYBEHPN6SIZWHUN6YNVIR4UGD/action/replication_record"}},"created_at":"2026-07-05T09:37:47.232366+00:00","updated_at":"2026-07-05T09:37:47.232366+00:00"}