{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W6UTP3MY2EF4F5A2MDGRE3HNSD","short_pith_number":"pith:W6UTP3MY","canonical_record":{"source":{"id":"2507.09574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T10:52:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a294a84ace8e87f345538817f879c41fe2f45ef8d21025d337ecd5928d5344c1","abstract_canon_sha256":"cbe066a2e41a00486c8b5fdb73aa1aa4bce5662ae6eb523cdc8644391fc3c1d5"},"schema_version":"1.0"},"canonical_sha256":"b7a937ed98d10bc2f41a60cd126ced90c2a71c3ddb779dbe1dbfb8eadd2a5798","source":{"kind":"arxiv","id":"2507.09574","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09574","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09574v3","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09574","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"W6UTP3MY2EF4","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"W6UTP3MY2EF4F5A2","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"W6UTP3MY","created_at":"2026-05-29T01:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W6UTP3MY2EF4F5A2MDGRE3HNSD","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T10:52:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a294a84ace8e87f345538817f879c41fe2f45ef8d21025d337ecd5928d5344c1","abstract_canon_sha256":"cbe066a2e41a00486c8b5fdb73aa1aa4bce5662ae6eb523cdc8644391fc3c1d5"},"schema_version":"1.0"},"canonical_sha256":"b7a937ed98d10bc2f41a60cd126ced90c2a71c3ddb779dbe1dbfb8eadd2a5798","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:54.401486Z","signature_b64":"BHpyYre+TaIIn3M8HN/UXCUgFCm7cB4bBP5Qt0meJCn+K1bldt0FFQ6tq55izG4pVas5Z2/boCg4yKgwK/ftAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7a937ed98d10bc2f41a60cd126ced90c2a71c3ddb779dbe1dbfb8eadd2a5798","last_reissued_at":"2026-05-29T01:04:54.399747Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:54.399747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09574","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":"2026-05-29T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/S1rwpfQqT9p7a4U6k0RNPBPVn9h1L3Lov6zHCTFt1fFgF3YOYvZbQTIEFKnUij9TV7MGdeB3u8/ZMv9ZitCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:35:44.165753Z"},"content_sha256":"4cb44b17dbd96a8e6c86240d7ecbc682b929930912bae32112fd6840b23567ba","schema_version":"1.0","event_id":"sha256:4cb44b17dbd96a8e6c86240d7ecbc682b929930912bae32112fd6840b23567ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W6UTP3MY2EF4F5A2MDGRE3HNSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haozhe Zhao, Jiuxiang Gu, Junjie Hu, Liang Chen, Minjia Zhang, Shuzheng Si, Wen Xiao, Zefan Cai","submitted_at":"2025-07-13T10:52:59Z","abstract_excerpt":"Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we propose MENTOR, a novel autoregressive (AR) framework for efficient Multimodal-conditioned Tuning for Autoregressive multimodal image generation. MENTOR combines an AR image generator with a two-stage training paradigm, enabling fine-grained, token-level alignment between multimodal inputs and image outputs without relying on auxiliary adapters or cross-att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09574","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/2507.09574/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":"2026-05-29T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijoDkWRtqg7BUkXthWxq5XxsFAl2ELMMb44vQY5RHzvMy7Ejr0lqBAHqkxuJGv7Je5ESInwa4NBKyc3lHu3hAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:35:44.166615Z"},"content_sha256":"b2e1ab2ad6b276aebbeab0ded7830d6d232afc76cd482d22d1649c95badd7d62","schema_version":"1.0","event_id":"sha256:b2e1ab2ad6b276aebbeab0ded7830d6d232afc76cd482d22d1649c95badd7d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/bundle.json","state_url":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/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":"2026-05-30T21:35:44Z","links":{"resolver":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD","bundle":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/bundle.json","state":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W6UTP3MY2EF4F5A2MDGRE3HNSD","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":"cbe066a2e41a00486c8b5fdb73aa1aa4bce5662ae6eb523cdc8644391fc3c1d5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T10:52:59Z","title_canon_sha256":"a294a84ace8e87f345538817f879c41fe2f45ef8d21025d337ecd5928d5344c1"},"schema_version":"1.0","source":{"id":"2507.09574","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09574","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09574v3","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09574","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"W6UTP3MY2EF4","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"W6UTP3MY2EF4F5A2","created_at":"2026-05-29T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"W6UTP3MY","created_at":"2026-05-29T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:b2e1ab2ad6b276aebbeab0ded7830d6d232afc76cd482d22d1649c95badd7d62","target":"graph","created_at":"2026-05-29T01:04:54Z","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/2507.09574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we propose MENTOR, a novel autoregressive (AR) framework for efficient Multimodal-conditioned Tuning for Autoregressive multimodal image generation. MENTOR combines an AR image generator with a two-stage training paradigm, enabling fine-grained, token-level alignment between multimodal inputs and image outputs without relying on auxiliary adapters or cross-att","authors_text":"Haozhe Zhao, Jiuxiang Gu, Junjie Hu, Liang Chen, Minjia Zhang, Shuzheng Si, Wen Xiao, Zefan Cai","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T10:52:59Z","title":"MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09574","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":"sha256:4cb44b17dbd96a8e6c86240d7ecbc682b929930912bae32112fd6840b23567ba","target":"record","created_at":"2026-05-29T01:04:54Z","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":"cbe066a2e41a00486c8b5fdb73aa1aa4bce5662ae6eb523cdc8644391fc3c1d5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T10:52:59Z","title_canon_sha256":"a294a84ace8e87f345538817f879c41fe2f45ef8d21025d337ecd5928d5344c1"},"schema_version":"1.0","source":{"id":"2507.09574","kind":"arxiv","version":3}},"canonical_sha256":"b7a937ed98d10bc2f41a60cd126ced90c2a71c3ddb779dbe1dbfb8eadd2a5798","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7a937ed98d10bc2f41a60cd126ced90c2a71c3ddb779dbe1dbfb8eadd2a5798","first_computed_at":"2026-05-29T01:04:54.399747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:54.399747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BHpyYre+TaIIn3M8HN/UXCUgFCm7cB4bBP5Qt0meJCn+K1bldt0FFQ6tq55izG4pVas5Z2/boCg4yKgwK/ftAg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:54.401486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09574","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cb44b17dbd96a8e6c86240d7ecbc682b929930912bae32112fd6840b23567ba","sha256:b2e1ab2ad6b276aebbeab0ded7830d6d232afc76cd482d22d1649c95badd7d62"],"state_sha256":"deff7411bc223539ded74a21a22abc39e480fb3f51522911dea6c1e486778c44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n3pw8Lt0ETHBCyzeeoh3vC6MO6+oTXSadEGARbdUSlM8c+VZlD71Y6sjSoc3t+Sb94zC/l5jdhLeqk3ZU+5uBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T21:35:44.172553Z","bundle_sha256":"79239fc6d8e0cd6b8350de9c9fa2c6b0a93ecd7e8db87f033dca29b964693498"}}