{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YINVLGZLH23ZIWV5OU5VHDGWCY","short_pith_number":"pith:YINVLGZL","canonical_record":{"source":{"id":"2506.07963","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"eacee94a89536a9fbeef33e25e6967703dd9e8bc78390f0821bead640bdb875c","abstract_canon_sha256":"f6fdfc510d60f43c481ec38a085b53db554f791e136652ec99d47b48e757c935"},"schema_version":"1.0"},"canonical_sha256":"c21b559b2b3eb7945abd753b538cd6162b1ed288a23b808241c116a5ebefb194","source":{"kind":"arxiv","id":"2506.07963","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07963","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07963v3","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07963","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"YINVLGZLH23Z","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"YINVLGZLH23ZIWV5","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"YINVLGZL","created_at":"2026-07-05T12:06:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YINVLGZLH23ZIWV5OU5VHDGWCY","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07963","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"eacee94a89536a9fbeef33e25e6967703dd9e8bc78390f0821bead640bdb875c","abstract_canon_sha256":"f6fdfc510d60f43c481ec38a085b53db554f791e136652ec99d47b48e757c935"},"schema_version":"1.0"},"canonical_sha256":"c21b559b2b3eb7945abd753b538cd6162b1ed288a23b808241c116a5ebefb194","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:48.373351Z","signature_b64":"gFSf/z+bxrBhbzJZk4GR1W0KqMFBxbrEzpojzbMBPeONdhMvmPGm6C6hxJc0+xnHJQ6Ptyg6MHnIes4kouLODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c21b559b2b3eb7945abd753b538cd6162b1ed288a23b808241c116a5ebefb194","last_reissued_at":"2026-07-05T12:06:48.372861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:48.372861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07963","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJaqXJrEJht3ZV/KWEaeZrca2FFmSV9h1BUl1WB+ZJWTWnMzQ6uhzJoErFxSqr25GAHZK2vXFe8IPZQ3BzW3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:51:36.951798Z"},"content_sha256":"a111227314ee7eb422b5046b55b4a3bc8ccaf1b953ea60533e24cd6688272734","schema_version":"1.0","event_id":"sha256:a111227314ee7eb422b5046b55b4a3bc8ccaf1b953ea60533e24cd6688272734"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YINVLGZLH23ZIWV5OU5VHDGWCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Guanzhong Wang, Ji-Rong Wen, Jixiang Hong, Rui Yan, Yi Liu, Yiran Zhang","submitted_at":"2025-06-09T17:38:45Z","abstract_excerpt":"Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are naturally inverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07963","kind":"arxiv","version":3},"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/2506.07963/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":"2026-07-05T12:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K45HifaK1C1+jxsWGzv5vJUMOzLANVtEiXOUdc/ruy5TceuBNGrS3HFz2l8xFcYDDbKecOHq6ranMX4nno4pCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:51:36.952308Z"},"content_sha256":"ef74fbaff15e2a13cdd7fc33c69c52cd2fe267f521950efd6b107c6aef76e517","schema_version":"1.0","event_id":"sha256:ef74fbaff15e2a13cdd7fc33c69c52cd2fe267f521950efd6b107c6aef76e517"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YINVLGZLH23ZIWV5OU5VHDGWCY/bundle.json","state_url":"https://pith.science/pith/YINVLGZLH23ZIWV5OU5VHDGWCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YINVLGZLH23ZIWV5OU5VHDGWCY/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":"2026-08-09T18:51:36Z","links":{"resolver":"https://pith.science/pith/YINVLGZLH23ZIWV5OU5VHDGWCY","bundle":"https://pith.science/pith/YINVLGZLH23ZIWV5OU5VHDGWCY/bundle.json","state":"https://pith.science/pith/YINVLGZLH23ZIWV5OU5VHDGWCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YINVLGZLH23ZIWV5OU5VHDGWCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YINVLGZLH23ZIWV5OU5VHDGWCY","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":"f6fdfc510d60f43c481ec38a085b53db554f791e136652ec99d47b48e757c935","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","title_canon_sha256":"eacee94a89536a9fbeef33e25e6967703dd9e8bc78390f0821bead640bdb875c"},"schema_version":"1.0","source":{"id":"2506.07963","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07963","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07963v3","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07963","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"YINVLGZLH23Z","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"YINVLGZLH23ZIWV5","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"YINVLGZL","created_at":"2026-07-05T12:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:ef74fbaff15e2a13cdd7fc33c69c52cd2fe267f521950efd6b107c6aef76e517","target":"graph","created_at":"2026-07-05T12:06:48Z","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/2506.07963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are naturally inverse ","authors_text":"Guanzhong Wang, Ji-Rong Wen, Jixiang Hong, Rui Yan, Yi Liu, Yiran Zhang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","title":"SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07963","kind":"arxiv","version":3},"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:a111227314ee7eb422b5046b55b4a3bc8ccaf1b953ea60533e24cd6688272734","target":"record","created_at":"2026-07-05T12:06:48Z","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":"f6fdfc510d60f43c481ec38a085b53db554f791e136652ec99d47b48e757c935","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","title_canon_sha256":"eacee94a89536a9fbeef33e25e6967703dd9e8bc78390f0821bead640bdb875c"},"schema_version":"1.0","source":{"id":"2506.07963","kind":"arxiv","version":3}},"canonical_sha256":"c21b559b2b3eb7945abd753b538cd6162b1ed288a23b808241c116a5ebefb194","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c21b559b2b3eb7945abd753b538cd6162b1ed288a23b808241c116a5ebefb194","first_computed_at":"2026-07-05T12:06:48.372861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:48.372861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFSf/z+bxrBhbzJZk4GR1W0KqMFBxbrEzpojzbMBPeONdhMvmPGm6C6hxJc0+xnHJQ6Ptyg6MHnIes4kouLODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:48.373351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07963","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a111227314ee7eb422b5046b55b4a3bc8ccaf1b953ea60533e24cd6688272734","sha256:ef74fbaff15e2a13cdd7fc33c69c52cd2fe267f521950efd6b107c6aef76e517"],"state_sha256":"e3ba06a18f08a0ef7b8524a730c1862ad0be73b7faf3f991578d6789a7af52b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9DCeR+n+9EdiY3UcXihj7N0GoVZiYlHdMTkMTlmlS+xUh/02spt6875sVvqaG8pgUOKxzurRS5a715HuQcBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:51:36.955667Z","bundle_sha256":"44b401a71afff50060e86a400adc64198b530585a5a825adc7dc5353ae7a373e"}}