{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CMK5435CCMC45FU53QYSU2TW4U","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":"73d6e35563f95d2487b059b5ebf98a7afe8b87f8444fdd31ccd4faacc0fe1d9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T08:06:00Z","title_canon_sha256":"4ab00beb2391238118abc0349ea63485fddd9c88da7b455bc9773a520f22d901"},"schema_version":"1.0","source":{"id":"2412.15650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15650","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15650v1","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15650","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"CMK5435CCMC4","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_16","alias_value":"CMK5435CCMC45FU5","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_8","alias_value":"CMK5435C","created_at":"2026-07-05T09:52:27Z"}],"graph_snapshots":[{"event_id":"sha256:d0553eac81459d7680811583dbdd026aeb264c1725ca05b27a09c75474a9fd5b","target":"graph","created_at":"2026-07-05T09:52:27Z","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/2412.15650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human preference alignment can greatly enhance Multimodal Large Language Models (MLLMs), but collecting high-quality preference data is costly. A promising solution is the self-evolution strategy, where models are iteratively trained on data they generate. However, current techniques still rely on human- or GPT-annotated data and sometimes require additional models or ground truth answers. To address these issues, we propose a novel multimodal self-evolution framework that enables the model to autonomously generate high-quality questions and answers using only unannotated images.\n  First, we i","authors_text":"Changxing Ding, Chao Xue, Qiong Cao, Wentao Tan, Yibing Zhan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T08:06:00Z","title":"Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15650","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:c2b2d2dc2ffe97c086db71fd3477fe93a95559475fe13348d54d3061a4abf890","target":"record","created_at":"2026-07-05T09:52:27Z","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":"73d6e35563f95d2487b059b5ebf98a7afe8b87f8444fdd31ccd4faacc0fe1d9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T08:06:00Z","title_canon_sha256":"4ab00beb2391238118abc0349ea63485fddd9c88da7b455bc9773a520f22d901"},"schema_version":"1.0","source":{"id":"2412.15650","kind":"arxiv","version":1}},"canonical_sha256":"1315de6fa21305ce969ddc312a6a76e52f2c16d2d9ccc135189808cf4931448d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1315de6fa21305ce969ddc312a6a76e52f2c16d2d9ccc135189808cf4931448d","first_computed_at":"2026-07-05T09:52:27.716102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:27.716102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LGP2kzlx1x/1lZcTg0y5N/itqt4xA7U9lJFFWhOZQFkOKfgVh3ZqJ0Nfj3GUBGt7id702pLXxGtcei/BmO8PDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:27.716593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2b2d2dc2ffe97c086db71fd3477fe93a95559475fe13348d54d3061a4abf890","sha256:d0553eac81459d7680811583dbdd026aeb264c1725ca05b27a09c75474a9fd5b"],"state_sha256":"012a82dfa3cccf2e831a851a1a8904f544312fb1716d73b70f8cc3a576d78b00"}