{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7WUN5SJIQDTK5NSBXZDD6HJGFO","short_pith_number":"pith:7WUN5SJI","canonical_record":{"source":{"id":"2312.06968","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T04:05:15Z","cross_cats_sorted":[],"title_canon_sha256":"0b507125cc005cc6ee202d7145655baaad0c778a7a079ee8503afcc88e03f4f5","abstract_canon_sha256":"9ff4572b66803b50e44f89c4d01f5e1c3ea2fa13f364804e8c525dc33d279ea1"},"schema_version":"1.0"},"canonical_sha256":"fda8dec92880e6aeb641be463f1d262bb46147e24c8d56fc778b2f21e8d621ff","source":{"kind":"arxiv","id":"2312.06968","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06968","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06968v4","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06968","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_12","alias_value":"7WUN5SJIQDTK","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_16","alias_value":"7WUN5SJIQDTK5NSB","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_8","alias_value":"7WUN5SJI","created_at":"2026-07-05T07:48:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7WUN5SJIQDTK5NSBXZDD6HJGFO","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06968","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T04:05:15Z","cross_cats_sorted":[],"title_canon_sha256":"0b507125cc005cc6ee202d7145655baaad0c778a7a079ee8503afcc88e03f4f5","abstract_canon_sha256":"9ff4572b66803b50e44f89c4d01f5e1c3ea2fa13f364804e8c525dc33d279ea1"},"schema_version":"1.0"},"canonical_sha256":"fda8dec92880e6aeb641be463f1d262bb46147e24c8d56fc778b2f21e8d621ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:51.034369Z","signature_b64":"71k96HaQVrw5doFVlcXJSOX2XOtwu/geQiO76xkudgMo4gaYxOxvdSCzTZRo3ntZ9Bz8mhBjur5GtrZJKmajDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda8dec92880e6aeb641be463f1d262bb46147e24c8d56fc778b2f21e8d621ff","last_reissued_at":"2026-07-05T07:48:51.033937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:51.033937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06968","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NAutszbaWtE5FWMPSr15tKGRs6BCcfo8KF+S++KZpg+wQnHpyCdYyhuuSalrv6dSzZFVMCF6W+YfIZKKMjjpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:19:08.253776Z"},"content_sha256":"8892df05990d1bdd7ab4cb86eceb002fcffcd001113daa81cd5b5dc3f4764bd6","schema_version":"1.0","event_id":"sha256:8892df05990d1bdd7ab4cb86eceb002fcffcd001113daa81cd5b5dc3f4764bd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7WUN5SJIQDTK5NSBXZDD6HJGFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hallucination Augmented Contrastive Learning for Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Jiaxing Chen, Ji Zhang, Mengfan Dong, Ming Yan, Qinghao Ye, Shikun Zhang, Wei Ye","submitted_at":"2023-12-12T04:05:15Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend to generate erroneous or fabricated information. In this paper, we address hallucinations in MLLMs from a novel perspective of representation learning. We first analyzed the representation distribution of textual and visual tokens in MLLM, revealing two important findings: 1) there is a significant gap between textual and visual representations, indicating un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06968","kind":"arxiv","version":4},"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/2312.06968/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":"2026-07-05T07:48:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUZHaE1dQZNuuZbj93JWrc0ppmMS0AmW9oFA9JBmSiWYfqqg1W1sdd9UEBEoOhXsmngWpBaiPZhG11iUrNKSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:19:08.254777Z"},"content_sha256":"19ddf4014ca4e1858511aeb3c5ac1d5a92e5126b3c48405a3c39f743b1a1ed96","schema_version":"1.0","event_id":"sha256:19ddf4014ca4e1858511aeb3c5ac1d5a92e5126b3c48405a3c39f743b1a1ed96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WUN5SJIQDTK5NSBXZDD6HJGFO/bundle.json","state_url":"https://pith.science/pith/7WUN5SJIQDTK5NSBXZDD6HJGFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WUN5SJIQDTK5NSBXZDD6HJGFO/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":"2026-08-17T16:19:08Z","links":{"resolver":"https://pith.science/pith/7WUN5SJIQDTK5NSBXZDD6HJGFO","bundle":"https://pith.science/pith/7WUN5SJIQDTK5NSBXZDD6HJGFO/bundle.json","state":"https://pith.science/pith/7WUN5SJIQDTK5NSBXZDD6HJGFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WUN5SJIQDTK5NSBXZDD6HJGFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7WUN5SJIQDTK5NSBXZDD6HJGFO","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":"9ff4572b66803b50e44f89c4d01f5e1c3ea2fa13f364804e8c525dc33d279ea1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T04:05:15Z","title_canon_sha256":"0b507125cc005cc6ee202d7145655baaad0c778a7a079ee8503afcc88e03f4f5"},"schema_version":"1.0","source":{"id":"2312.06968","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06968","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06968v4","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06968","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_12","alias_value":"7WUN5SJIQDTK","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_16","alias_value":"7WUN5SJIQDTK5NSB","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_8","alias_value":"7WUN5SJI","created_at":"2026-07-05T07:48:51Z"}],"graph_snapshots":[{"event_id":"sha256:19ddf4014ca4e1858511aeb3c5ac1d5a92e5126b3c48405a3c39f743b1a1ed96","target":"graph","created_at":"2026-07-05T07:48:51Z","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/2312.06968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend to generate erroneous or fabricated information. In this paper, we address hallucinations in MLLMs from a novel perspective of representation learning. We first analyzed the representation distribution of textual and visual tokens in MLLM, revealing two important findings: 1) there is a significant gap between textual and visual representations, indicating un","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Jiaxing Chen, Ji Zhang, Mengfan Dong, Ming Yan, Qinghao Ye, Shikun Zhang, Wei Ye","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T04:05:15Z","title":"Hallucination Augmented Contrastive Learning for Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06968","kind":"arxiv","version":4},"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":"sha256:8892df05990d1bdd7ab4cb86eceb002fcffcd001113daa81cd5b5dc3f4764bd6","target":"record","created_at":"2026-07-05T07:48:51Z","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":"9ff4572b66803b50e44f89c4d01f5e1c3ea2fa13f364804e8c525dc33d279ea1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T04:05:15Z","title_canon_sha256":"0b507125cc005cc6ee202d7145655baaad0c778a7a079ee8503afcc88e03f4f5"},"schema_version":"1.0","source":{"id":"2312.06968","kind":"arxiv","version":4}},"canonical_sha256":"fda8dec92880e6aeb641be463f1d262bb46147e24c8d56fc778b2f21e8d621ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fda8dec92880e6aeb641be463f1d262bb46147e24c8d56fc778b2f21e8d621ff","first_computed_at":"2026-07-05T07:48:51.033937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:51.033937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"71k96HaQVrw5doFVlcXJSOX2XOtwu/geQiO76xkudgMo4gaYxOxvdSCzTZRo3ntZ9Bz8mhBjur5GtrZJKmajDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:51.034369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06968","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8892df05990d1bdd7ab4cb86eceb002fcffcd001113daa81cd5b5dc3f4764bd6","sha256:19ddf4014ca4e1858511aeb3c5ac1d5a92e5126b3c48405a3c39f743b1a1ed96"],"state_sha256":"3c824c04373ba367fa0995713ffd542742e76236752358d93a69b3877f523b13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbR9nPLpYaqILf3rb9Tmou3udr2ulDcQwdykeYsuxQGjwuVwvki7066QIVgpzFS+ITYC/k8k9qx3Dn2Oymm9Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:19:08.275176Z","bundle_sha256":"67a3c4a12e802c71a4e76ad666f0982ed0102bcd0ba79feb20660abc0f091f32"}}