{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:U6HXRAVQ2RFQ4EGYSJVN6HZ2M4","short_pith_number":"pith:U6HXRAVQ","canonical_record":{"source":{"id":"2605.18714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:46:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"518861457b62f2f2a5bad305445d93c993f36983dee51603519df02ac49be00e","abstract_canon_sha256":"f9b9fc1d75266deff49cb73eb91daec88d848c178fdf95edc1c11f759918b9ee"},"schema_version":"1.0"},"canonical_sha256":"a78f7882b0d44b0e10d8926adf1f3a67207a957dd2715ac309c79cfd1dbd7af5","source":{"kind":"arxiv","id":"2605.18714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18714","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18714v1","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18714","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"U6HXRAVQ2RFQ","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"U6HXRAVQ2RFQ4EGY","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"U6HXRAVQ","created_at":"2026-05-20T00:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:U6HXRAVQ2RFQ4EGYSJVN6HZ2M4","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:46:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"518861457b62f2f2a5bad305445d93c993f36983dee51603519df02ac49be00e","abstract_canon_sha256":"f9b9fc1d75266deff49cb73eb91daec88d848c178fdf95edc1c11f759918b9ee"},"schema_version":"1.0"},"canonical_sha256":"a78f7882b0d44b0e10d8926adf1f3a67207a957dd2715ac309c79cfd1dbd7af5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:16.621152Z","signature_b64":"jLUTgfVZkRzv7rmLE91ryV8I1Di6uYHX77ukswUVGnpDmodQ94Kca+LfZjiEY2/6vugRWpVRW6pbO8sz/BVUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a78f7882b0d44b0e10d8926adf1f3a67207a957dd2715ac309c79cfd1dbd7af5","last_reissued_at":"2026-05-20T00:06:16.620386Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:16.620386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18714","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kd8XziRwZa4QbdVHCQMdkXZe+Q6ljPvZ/f/2Ntv/l9a4nNDC/iuo5CiNoYEulGGhIC+LkV5pujkXxVPH0EpvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T10:36:25.785560Z"},"content_sha256":"8442e02af840a468d04150e0f75029bec1821fb1d301062508a93d4c63d555d1","schema_version":"1.0","event_id":"sha256:8442e02af840a468d04150e0f75029bec1821fb1d301062508a93d4c63d555d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:U6HXRAVQ2RFQ4EGYSJVN6HZ2M4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Generative Tuning for Unified Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Songsong Yu, Yanwei Li, Ying Shan, Yuxin Chen","submitted_at":"2026-05-18T17:46:46Z","abstract_excerpt":"Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training paradigms independently optimize understanding via sparse text signals and generation through dense pixel objectives. Such a decoupled strategy yields misaligned representation spaces, isolating visual understanding from generation and hindering their mutual reinforcement. This work presents the first systematic investigation into generative post-training, where we formulate hierarchical visual tasks as generative proxies to bridge the iso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18714","kind":"arxiv","version":1},"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/2605.18714/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.052671Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8fb31a1339a6cdfd699aaf3e06ee136f8533312199de10838a2456307b62bf4f"},"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":"2026-05-20T00:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0SkVE1CyGd6G6haLVzwnvY8s4t/UXCFxvtAgsaK62UvYccPgA/K5Eu+kl5ag7KwF0SNBFycq+sYYezhCJiR8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T10:36:25.786343Z"},"content_sha256":"440d93dfe6451ced8c3de1fa336edc2f20a4f5b87ecef6c7a67d7657f14d3054","schema_version":"1.0","event_id":"sha256:440d93dfe6451ced8c3de1fa336edc2f20a4f5b87ecef6c7a67d7657f14d3054"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6HXRAVQ2RFQ4EGYSJVN6HZ2M4/bundle.json","state_url":"https://pith.science/pith/U6HXRAVQ2RFQ4EGYSJVN6HZ2M4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6HXRAVQ2RFQ4EGYSJVN6HZ2M4/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":"2026-05-22T10:36:25Z","links":{"resolver":"https://pith.science/pith/U6HXRAVQ2RFQ4EGYSJVN6HZ2M4","bundle":"https://pith.science/pith/U6HXRAVQ2RFQ4EGYSJVN6HZ2M4/bundle.json","state":"https://pith.science/pith/U6HXRAVQ2RFQ4EGYSJVN6HZ2M4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6HXRAVQ2RFQ4EGYSJVN6HZ2M4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U6HXRAVQ2RFQ4EGYSJVN6HZ2M4","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":"f9b9fc1d75266deff49cb73eb91daec88d848c178fdf95edc1c11f759918b9ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:46:46Z","title_canon_sha256":"518861457b62f2f2a5bad305445d93c993f36983dee51603519df02ac49be00e"},"schema_version":"1.0","source":{"id":"2605.18714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18714","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18714v1","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18714","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"U6HXRAVQ2RFQ","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"U6HXRAVQ2RFQ4EGY","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"U6HXRAVQ","created_at":"2026-05-20T00:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:440d93dfe6451ced8c3de1fa336edc2f20a4f5b87ecef6c7a67d7657f14d3054","target":"graph","created_at":"2026-05-20T00:06:16Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.052671Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18714/integrity.json","findings":[],"snapshot_sha256":"8fb31a1339a6cdfd699aaf3e06ee136f8533312199de10838a2456307b62bf4f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training paradigms independently optimize understanding via sparse text signals and generation through dense pixel objectives. Such a decoupled strategy yields misaligned representation spaces, isolating visual understanding from generation and hindering their mutual reinforcement. This work presents the first systematic investigation into generative post-training, where we formulate hierarchical visual tasks as generative proxies to bridge the iso","authors_text":"Songsong Yu, Yanwei Li, Ying Shan, Yuxin Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:46:46Z","title":"Semantic Generative Tuning for Unified Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18714","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":"sha256:8442e02af840a468d04150e0f75029bec1821fb1d301062508a93d4c63d555d1","target":"record","created_at":"2026-05-20T00:06:16Z","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":"f9b9fc1d75266deff49cb73eb91daec88d848c178fdf95edc1c11f759918b9ee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:46:46Z","title_canon_sha256":"518861457b62f2f2a5bad305445d93c993f36983dee51603519df02ac49be00e"},"schema_version":"1.0","source":{"id":"2605.18714","kind":"arxiv","version":1}},"canonical_sha256":"a78f7882b0d44b0e10d8926adf1f3a67207a957dd2715ac309c79cfd1dbd7af5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a78f7882b0d44b0e10d8926adf1f3a67207a957dd2715ac309c79cfd1dbd7af5","first_computed_at":"2026-05-20T00:06:16.620386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:16.620386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jLUTgfVZkRzv7rmLE91ryV8I1Di6uYHX77ukswUVGnpDmodQ94Kca+LfZjiEY2/6vugRWpVRW6pbO8sz/BVUBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:16.621152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8442e02af840a468d04150e0f75029bec1821fb1d301062508a93d4c63d555d1","sha256:440d93dfe6451ced8c3de1fa336edc2f20a4f5b87ecef6c7a67d7657f14d3054"],"state_sha256":"2ac7ed40aec07854f26cd3d7de5fe15809dc25734a6f44c4a57d09698c7d6ffb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GcW9BAUEUVZ5t5w9HTGl8lGvonaLj0kaUK+bcAE9rgKNk8ERJgcVQF7qJcRwk+o710Yqdf/piuzlygpB0jw8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T10:36:25.790388Z","bundle_sha256":"97f348aea18c68b3f4d43b8f8d185a5d7393188630f6a9c6d69bf17380b2b1e1"}}