{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QALTJZHCAC4G2YCJXDGSAETXLM","short_pith_number":"pith:QALTJZHC","canonical_record":{"source":{"id":"2405.15973","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T23:09:27Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fb486e44bddb48ae5e952d561cc17e93308996e71d1ffeb563e11b2df94252eb","abstract_canon_sha256":"f5e46bb4ca15ddcc68b99228099960d517df1e1dfc461ee6a6fb765528bfaa50"},"schema_version":"1.0"},"canonical_sha256":"801734e4e200b86d6049b8cd2012775b03e9e0e11f57f2f78eb1048ef34b9fee","source":{"kind":"arxiv","id":"2405.15973","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15973","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15973v4","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15973","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"QALTJZHCAC4G","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"QALTJZHCAC4G2YCJ","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"QALTJZHC","created_at":"2026-07-05T10:11:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QALTJZHCAC4G2YCJXDGSAETXLM","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15973","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T23:09:27Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fb486e44bddb48ae5e952d561cc17e93308996e71d1ffeb563e11b2df94252eb","abstract_canon_sha256":"f5e46bb4ca15ddcc68b99228099960d517df1e1dfc461ee6a6fb765528bfaa50"},"schema_version":"1.0"},"canonical_sha256":"801734e4e200b86d6049b8cd2012775b03e9e0e11f57f2f78eb1048ef34b9fee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:19.836899Z","signature_b64":"pkzVgsNroEJjptlbIgmGobmfs4qD6Zu3YtejqP5BuZ7WZY+4GPtjZteTAaLTXrsCuTZUZ63Rnr2I64uGwcw+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"801734e4e200b86d6049b8cd2012775b03e9e0e11f57f2f78eb1048ef34b9fee","last_reissued_at":"2026-07-05T10:11:19.836396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:19.836396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15973","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":"2026-07-05T10:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wx3RThq5c8ZbwEHbHulJ662shS6q64xPdeeTfTwy4DWLjMVFLcOEA0/vAJtZVVWNNVnRTatskLlOOLQlSF5zAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:25:45.354491Z"},"content_sha256":"0820a58c0ed4e796c37c369be873233f82ad83d9c996337b1e699d791894e391","schema_version":"1.0","event_id":"sha256:0820a58c0ed4e796c37c369be873233f82ad83d9c996337b1e699d791894e391"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QALTJZHCAC4G2YCJXDGSAETXLM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cao Xiao, Furong Huang, Huaxiu Yao, Jiuhai Chen, Parminder Bhatia, Tianyi Zhou, Tom Goldstein, Xiyao Wang, Yiyang Zhou, Yuhang Zhou, Zhaoyang Wang","submitted_at":"2024-05-24T23:09:27Z","abstract_excerpt":"Large vision-language models (LVLMs) have achieved impressive results in visual question-answering and reasoning tasks through vision instruction tuning on specific datasets. However, there remains significant room for improvement in aligning visual and language modalities. Existing methods often depend on external models or data, leading to uncontrollable and unstable alignment results. In this paper, we propose SIMA, a self-improvement framework that enhances visual and language modality alignment without external dependencies. SIMA leverages existing vision instruction tuning datasets to se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15973","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/2405.15973/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":"2026-07-05T10:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"274iVGW7gz7+87fBIZubz37eXkuuZtLvIQNUcWGFQfG7lx2FkyXa8KEx17l3gRonorenD6iuNGKXBDD0ZlrjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:25:45.354905Z"},"content_sha256":"9a0dbb2005a701c9a54d42d38dd14713218fee76be03db9d15706b683467f2e2","schema_version":"1.0","event_id":"sha256:9a0dbb2005a701c9a54d42d38dd14713218fee76be03db9d15706b683467f2e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QALTJZHCAC4G2YCJXDGSAETXLM/bundle.json","state_url":"https://pith.science/pith/QALTJZHCAC4G2YCJXDGSAETXLM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QALTJZHCAC4G2YCJXDGSAETXLM/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":"2026-08-04T21:25:45Z","links":{"resolver":"https://pith.science/pith/QALTJZHCAC4G2YCJXDGSAETXLM","bundle":"https://pith.science/pith/QALTJZHCAC4G2YCJXDGSAETXLM/bundle.json","state":"https://pith.science/pith/QALTJZHCAC4G2YCJXDGSAETXLM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QALTJZHCAC4G2YCJXDGSAETXLM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QALTJZHCAC4G2YCJXDGSAETXLM","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":"f5e46bb4ca15ddcc68b99228099960d517df1e1dfc461ee6a6fb765528bfaa50","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T23:09:27Z","title_canon_sha256":"fb486e44bddb48ae5e952d561cc17e93308996e71d1ffeb563e11b2df94252eb"},"schema_version":"1.0","source":{"id":"2405.15973","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15973","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15973v4","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15973","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"QALTJZHCAC4G","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"QALTJZHCAC4G2YCJ","created_at":"2026-07-05T10:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"QALTJZHC","created_at":"2026-07-05T10:11:19Z"}],"graph_snapshots":[{"event_id":"sha256:9a0dbb2005a701c9a54d42d38dd14713218fee76be03db9d15706b683467f2e2","target":"graph","created_at":"2026-07-05T10:11:19Z","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/2405.15973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) have achieved impressive results in visual question-answering and reasoning tasks through vision instruction tuning on specific datasets. However, there remains significant room for improvement in aligning visual and language modalities. Existing methods often depend on external models or data, leading to uncontrollable and unstable alignment results. In this paper, we propose SIMA, a self-improvement framework that enhances visual and language modality alignment without external dependencies. SIMA leverages existing vision instruction tuning datasets to se","authors_text":"Cao Xiao, Furong Huang, Huaxiu Yao, Jiuhai Chen, Parminder Bhatia, Tianyi Zhou, Tom Goldstein, Xiyao Wang, Yiyang Zhou, Yuhang Zhou, Zhaoyang Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T23:09:27Z","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15973","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":"sha256:0820a58c0ed4e796c37c369be873233f82ad83d9c996337b1e699d791894e391","target":"record","created_at":"2026-07-05T10:11:19Z","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":"f5e46bb4ca15ddcc68b99228099960d517df1e1dfc461ee6a6fb765528bfaa50","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T23:09:27Z","title_canon_sha256":"fb486e44bddb48ae5e952d561cc17e93308996e71d1ffeb563e11b2df94252eb"},"schema_version":"1.0","source":{"id":"2405.15973","kind":"arxiv","version":4}},"canonical_sha256":"801734e4e200b86d6049b8cd2012775b03e9e0e11f57f2f78eb1048ef34b9fee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"801734e4e200b86d6049b8cd2012775b03e9e0e11f57f2f78eb1048ef34b9fee","first_computed_at":"2026-07-05T10:11:19.836396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:19.836396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pkzVgsNroEJjptlbIgmGobmfs4qD6Zu3YtejqP5BuZ7WZY+4GPtjZteTAaLTXrsCuTZUZ63Rnr2I64uGwcw+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:19.836899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15973","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0820a58c0ed4e796c37c369be873233f82ad83d9c996337b1e699d791894e391","sha256:9a0dbb2005a701c9a54d42d38dd14713218fee76be03db9d15706b683467f2e2"],"state_sha256":"7e3162e9115169050283c03b231b48f47cde683b398a51b32fd57249ba0d06b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DJFA4Q/xJiZF1lPRA42VttoUrU5KH7jnAo1g5UHyE0mpXR5y0EA4uVgfZQWYhtIZW/0N4cfv1ZAIaEO/HfVYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:25:45.358010Z","bundle_sha256":"8d1936f82b4787f67c25fe496fe8f638e1674aa5d1360cbf254b851127f1ee57"}}