{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U6V27PZAMGDSOR2GMVE5M2ZZTA","short_pith_number":"pith:U6V27PZA","canonical_record":{"source":{"id":"2404.05046","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T19:00:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7db48c0403de01257e617dc65405627e61ce3c5b3e0b7aa45b5df50283c7977e","abstract_canon_sha256":"6c9e5a9384b5f16b5d24e29c128948474de5b037123992e38873993de47f8b4d"},"schema_version":"1.0"},"canonical_sha256":"a7abafbf2061872747466549d66b39983b4056c13c64fd043a433693a1e0bdc6","source":{"kind":"arxiv","id":"2404.05046","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05046","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05046v2","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05046","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"U6V27PZAMGDS","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"pith_short_16","alias_value":"U6V27PZAMGDSOR2G","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"pith_short_8","alias_value":"U6V27PZA","created_at":"2026-07-05T10:58:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U6V27PZAMGDSOR2GMVE5M2ZZTA","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05046","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T19:00:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7db48c0403de01257e617dc65405627e61ce3c5b3e0b7aa45b5df50283c7977e","abstract_canon_sha256":"6c9e5a9384b5f16b5d24e29c128948474de5b037123992e38873993de47f8b4d"},"schema_version":"1.0"},"canonical_sha256":"a7abafbf2061872747466549d66b39983b4056c13c64fd043a433693a1e0bdc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:59.733540Z","signature_b64":"jMRbWyt6Dgy0/eO0dypNI9dLUhrz87+N9wxtajLW0RmqcaKT3fpS2Wd0XAPw4tW6xt3ZzGVLyo+xVNjcu/0CDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7abafbf2061872747466549d66b39983b4056c13c64fd043a433693a1e0bdc6","last_reissued_at":"2026-07-05T10:58:59.733033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:59.733033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05046","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:58:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0bLcP7v+QtWqpRh+PsaDVPvk4NNo0YVV8+sug5tkhosa/qJ8Z+/AB5uoYJuJBf9NN7iv5j7x1NwX66yb6g8DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:00:32.403157Z"},"content_sha256":"5cc7583c8380220363892081ff7c19099ea8a0566718c22d2ea77f6a2afafd2e","schema_version":"1.0","event_id":"sha256:5cc7583c8380220363892081ff7c19099ea8a0566718c22d2ea77f6a2afafd2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U6V27PZAMGDSOR2GMVE5M2ZZTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Liqiang Jing, Xinya Du","submitted_at":"2024-04-07T19:00:45Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i.e., object existence, object attribute, and object relationship. To tackle this issue, existing methods mainly utilize Reinforcement Learning (RL) to align modalities in LVLMs. However, they still suffer from three main limitations: (1) General feedback can not indicate the hallucination type contained in the response; (2) Sparse rewards only give"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05046","kind":"arxiv","version":2},"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/2404.05046/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":"2026-07-05T10:58:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aob5sup4pUh4XPTU/wkziG19ckqo8QwqbY5VsVx2cUFAa5RbIzsyCJ9zTL8PJS8/NfX1HQT06xC7BTbLfIT2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:00:32.403647Z"},"content_sha256":"cdfa0cc81f05def48c9847c66302bf4409b1d22edf146ed85b257f00bbe3f701","schema_version":"1.0","event_id":"sha256:cdfa0cc81f05def48c9847c66302bf4409b1d22edf146ed85b257f00bbe3f701"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6V27PZAMGDSOR2GMVE5M2ZZTA/bundle.json","state_url":"https://pith.science/pith/U6V27PZAMGDSOR2GMVE5M2ZZTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6V27PZAMGDSOR2GMVE5M2ZZTA/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":"2026-08-09T03:00:32Z","links":{"resolver":"https://pith.science/pith/U6V27PZAMGDSOR2GMVE5M2ZZTA","bundle":"https://pith.science/pith/U6V27PZAMGDSOR2GMVE5M2ZZTA/bundle.json","state":"https://pith.science/pith/U6V27PZAMGDSOR2GMVE5M2ZZTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6V27PZAMGDSOR2GMVE5M2ZZTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U6V27PZAMGDSOR2GMVE5M2ZZTA","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":"6c9e5a9384b5f16b5d24e29c128948474de5b037123992e38873993de47f8b4d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T19:00:45Z","title_canon_sha256":"7db48c0403de01257e617dc65405627e61ce3c5b3e0b7aa45b5df50283c7977e"},"schema_version":"1.0","source":{"id":"2404.05046","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05046","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05046v2","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05046","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"U6V27PZAMGDS","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"pith_short_16","alias_value":"U6V27PZAMGDSOR2G","created_at":"2026-07-05T10:58:59Z"},{"alias_kind":"pith_short_8","alias_value":"U6V27PZA","created_at":"2026-07-05T10:58:59Z"}],"graph_snapshots":[{"event_id":"sha256:cdfa0cc81f05def48c9847c66302bf4409b1d22edf146ed85b257f00bbe3f701","target":"graph","created_at":"2026-07-05T10:58:59Z","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/2404.05046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i.e., object existence, object attribute, and object relationship. To tackle this issue, existing methods mainly utilize Reinforcement Learning (RL) to align modalities in LVLMs. However, they still suffer from three main limitations: (1) General feedback can not indicate the hallucination type contained in the response; (2) Sparse rewards only give","authors_text":"Liqiang Jing, Xinya Du","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T19:00:45Z","title":"FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05046","kind":"arxiv","version":2},"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":"sha256:5cc7583c8380220363892081ff7c19099ea8a0566718c22d2ea77f6a2afafd2e","target":"record","created_at":"2026-07-05T10:58:59Z","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":"6c9e5a9384b5f16b5d24e29c128948474de5b037123992e38873993de47f8b4d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T19:00:45Z","title_canon_sha256":"7db48c0403de01257e617dc65405627e61ce3c5b3e0b7aa45b5df50283c7977e"},"schema_version":"1.0","source":{"id":"2404.05046","kind":"arxiv","version":2}},"canonical_sha256":"a7abafbf2061872747466549d66b39983b4056c13c64fd043a433693a1e0bdc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7abafbf2061872747466549d66b39983b4056c13c64fd043a433693a1e0bdc6","first_computed_at":"2026-07-05T10:58:59.733033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:59.733033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jMRbWyt6Dgy0/eO0dypNI9dLUhrz87+N9wxtajLW0RmqcaKT3fpS2Wd0XAPw4tW6xt3ZzGVLyo+xVNjcu/0CDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:59.733540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05046","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cc7583c8380220363892081ff7c19099ea8a0566718c22d2ea77f6a2afafd2e","sha256:cdfa0cc81f05def48c9847c66302bf4409b1d22edf146ed85b257f00bbe3f701"],"state_sha256":"e0521fd1bbadcfd3729c8ed2ba3a2a93cda60530267da6bc240fa65f9615ce99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Qklc846G9dm1Bnx/jHFkRJG4jNmbjXbrZCcdVB/xqmiTihECBQSJFCenUxFX00E/U0yyz0ldYQVLwq4Kl8sDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:00:32.406917Z","bundle_sha256":"b9f036e34f5e280e6e57119786acdb1fc96d24b913bf403b7fe729c8a949c024"}}