{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z32IJB2T4AY5KOXQA3LOMMMNBH","short_pith_number":"pith:Z32IJB2T","canonical_record":{"source":{"id":"2409.14484","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"04b5fab90e007c1f172d3773ab34f75e4c13499f4aca7aaed120f2ec6e166360","abstract_canon_sha256":"1fda09cd918bcfbf6371d80f61349c215e644f975d12dd4955e2c5068fd734c8"},"schema_version":"1.0"},"canonical_sha256":"cef4848753e031d53af006d6e6318d09d62cb9beefe25c7fb9ac28255df4f7a9","source":{"kind":"arxiv","id":"2409.14484","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14484","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14484v1","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14484","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"Z32IJB2T4AY5","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"Z32IJB2T4AY5KOXQ","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"Z32IJB2T","created_at":"2026-07-05T09:10:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z32IJB2T4AY5KOXQA3LOMMMNBH","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14484","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"04b5fab90e007c1f172d3773ab34f75e4c13499f4aca7aaed120f2ec6e166360","abstract_canon_sha256":"1fda09cd918bcfbf6371d80f61349c215e644f975d12dd4955e2c5068fd734c8"},"schema_version":"1.0"},"canonical_sha256":"cef4848753e031d53af006d6e6318d09d62cb9beefe25c7fb9ac28255df4f7a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:17.559845Z","signature_b64":"ERqCTHA9xsxSD5gRIE8pkX/8tq0nF4AJArdgfZjflnXLF6xTbD5alVfKCCwH7E5vc27+ST1xny09IRZBSRjPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef4848753e031d53af006d6e6318d09d62cb9beefe25c7fb9ac28255df4f7a9","last_reissued_at":"2026-07-05T09:10:17.559457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:17.559457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14484","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":"2026-07-05T09:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XV6JUBKzUPWGR+OG/nfA5Kp1shbMUrtL/Ia7R6SamE/+ldU/u4kFrkUzdGb0zL7ABD54IVDa1tqmyhEOx4hMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:46:31.981314Z"},"content_sha256":"acc9dbf512dac375eca4b368a78ff5ac1df36db6e9122389396aa4996453c771","schema_version":"1.0","event_id":"sha256:acc9dbf512dac375eca4b368a78ff5ac1df36db6e9122389396aa4996453c771"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z32IJB2T4AY5KOXQA3LOMMMNBH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Wang, Jiyuan Zhang, Minyi Zhao, Shuigeng Zhou, Zhaoyang Li, Zhenbang Sun","submitted_at":"2024-09-22T15:07:18Z","abstract_excerpt":"Recent studies have shown that Vision Language Large Models (VLLMs) may output content not relevant to the input images. This problem, called the hallucination phenomenon, undoubtedly degrades VLLM performance. Therefore, various anti-hallucination techniques have been proposed to make model output more reasonable and accurate. Despite their successes, from extensive tests we found that augmenting the prompt (e.g. word appending, rewriting, and spell error etc.) may change model output and make the output hallucinate again. To cure this drawback, we propose a new instruct-tuning framework call"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14484","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/2409.14484/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":"2026-07-05T09:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b3KIz1riuO+h0cYgX9VdCQV6EUkuD/lXSMT4xfvCDdlC6yU6NGtKm8Pb5GOTT1dxw9Z1lk6jrZZvUWR2dJ1tBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:46:31.981822Z"},"content_sha256":"8593bb8e057c4609b7dd7248dacaf3f2d57d5a6fa452530ca24869898f17b381","schema_version":"1.0","event_id":"sha256:8593bb8e057c4609b7dd7248dacaf3f2d57d5a6fa452530ca24869898f17b381"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z32IJB2T4AY5KOXQA3LOMMMNBH/bundle.json","state_url":"https://pith.science/pith/Z32IJB2T4AY5KOXQA3LOMMMNBH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z32IJB2T4AY5KOXQA3LOMMMNBH/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":"2026-08-23T11:46:31Z","links":{"resolver":"https://pith.science/pith/Z32IJB2T4AY5KOXQA3LOMMMNBH","bundle":"https://pith.science/pith/Z32IJB2T4AY5KOXQA3LOMMMNBH/bundle.json","state":"https://pith.science/pith/Z32IJB2T4AY5KOXQA3LOMMMNBH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z32IJB2T4AY5KOXQA3LOMMMNBH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z32IJB2T4AY5KOXQA3LOMMMNBH","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":"1fda09cd918bcfbf6371d80f61349c215e644f975d12dd4955e2c5068fd734c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:07:18Z","title_canon_sha256":"04b5fab90e007c1f172d3773ab34f75e4c13499f4aca7aaed120f2ec6e166360"},"schema_version":"1.0","source":{"id":"2409.14484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14484","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14484v1","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14484","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"Z32IJB2T4AY5","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"Z32IJB2T4AY5KOXQ","created_at":"2026-07-05T09:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"Z32IJB2T","created_at":"2026-07-05T09:10:17Z"}],"graph_snapshots":[{"event_id":"sha256:8593bb8e057c4609b7dd7248dacaf3f2d57d5a6fa452530ca24869898f17b381","target":"graph","created_at":"2026-07-05T09:10:17Z","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/2409.14484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have shown that Vision Language Large Models (VLLMs) may output content not relevant to the input images. This problem, called the hallucination phenomenon, undoubtedly degrades VLLM performance. Therefore, various anti-hallucination techniques have been proposed to make model output more reasonable and accurate. Despite their successes, from extensive tests we found that augmenting the prompt (e.g. word appending, rewriting, and spell error etc.) may change model output and make the output hallucinate again. To cure this drawback, we propose a new instruct-tuning framework call","authors_text":"Jie Wang, Jiyuan Zhang, Minyi Zhao, Shuigeng Zhou, Zhaoyang Li, Zhenbang Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:07:18Z","title":"Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14484","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:acc9dbf512dac375eca4b368a78ff5ac1df36db6e9122389396aa4996453c771","target":"record","created_at":"2026-07-05T09:10:17Z","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":"1fda09cd918bcfbf6371d80f61349c215e644f975d12dd4955e2c5068fd734c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:07:18Z","title_canon_sha256":"04b5fab90e007c1f172d3773ab34f75e4c13499f4aca7aaed120f2ec6e166360"},"schema_version":"1.0","source":{"id":"2409.14484","kind":"arxiv","version":1}},"canonical_sha256":"cef4848753e031d53af006d6e6318d09d62cb9beefe25c7fb9ac28255df4f7a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cef4848753e031d53af006d6e6318d09d62cb9beefe25c7fb9ac28255df4f7a9","first_computed_at":"2026-07-05T09:10:17.559457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:17.559457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ERqCTHA9xsxSD5gRIE8pkX/8tq0nF4AJArdgfZjflnXLF6xTbD5alVfKCCwH7E5vc27+ST1xny09IRZBSRjPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:17.559845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acc9dbf512dac375eca4b368a78ff5ac1df36db6e9122389396aa4996453c771","sha256:8593bb8e057c4609b7dd7248dacaf3f2d57d5a6fa452530ca24869898f17b381"],"state_sha256":"cf0f6a3333406ba44e82c3e9a61fc22ee2bc871b53911508c2e2d061df6db66c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nMr8vSif/DcIzbkfkthSVya8x6bfhBrxBAxPaSUwerqXZ7dqG87C+rPhB1S5v/ZpBWX07GTtU01gms0okpcJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T11:46:31.986655Z","bundle_sha256":"b17f3c6aa3031b2d3fa66e66dfece2cc788d646094192ca89bc0c11fbfd94b04"}}