{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EN5VB2LH42MWDRG7777COSEXVR","short_pith_number":"pith:EN5VB2LH","canonical_record":{"source":{"id":"2505.23043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:40:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed286186d62cfcb27dd49215a0a8d686e68c42ddfefc7c11aadc9dcf6185378d","abstract_canon_sha256":"63a374a03e492d3310f61c10cda0cffeda36eadac3a2ed8ab35e8f9ff7933a51"},"schema_version":"1.0"},"canonical_sha256":"237b50e967e69961c4dffffe274897ac48470193cdc9dfb06668b47148b2bf88","source":{"kind":"arxiv","id":"2505.23043","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23043","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23043v1","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23043","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_12","alias_value":"EN5VB2LH42MW","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_16","alias_value":"EN5VB2LH42MWDRG7","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_8","alias_value":"EN5VB2LH","created_at":"2026-07-05T11:11:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EN5VB2LH42MWDRG7777COSEXVR","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:40:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed286186d62cfcb27dd49215a0a8d686e68c42ddfefc7c11aadc9dcf6185378d","abstract_canon_sha256":"63a374a03e492d3310f61c10cda0cffeda36eadac3a2ed8ab35e8f9ff7933a51"},"schema_version":"1.0"},"canonical_sha256":"237b50e967e69961c4dffffe274897ac48470193cdc9dfb06668b47148b2bf88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:54.252696Z","signature_b64":"eGiGRto+d2wSn40vIzmWBRDzr9SojhLIuW/iFJsksxLeycYIH8+0aIVea+1Vd6bPJoTBjDSp/y8nsd09OmR0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"237b50e967e69961c4dffffe274897ac48470193cdc9dfb06668b47148b2bf88","last_reissued_at":"2026-07-05T11:11:54.252143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:54.252143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23043","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":"2026-07-05T11:11:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cH8Dv0s7lOlKVNFWn5OdCUkRDCmLBknma23bV860p9phvWqK8yAtWlnpUaQTpKS2UOZe9RBe0gr6mqV7HmlcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:38:59.546941Z"},"content_sha256":"8e57b9673e11252d3517ea5a10d4d12198283f1ea9509518f450be1b6135664b","schema_version":"1.0","event_id":"sha256:8e57b9673e11252d3517ea5a10d4d12198283f1ea9509518f450be1b6135664b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EN5VB2LH42MWDRG7777COSEXVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jihai Zhang, Linjie Li, Tianle Li, Yu Cheng, Zhengyuan Yang","submitted_at":"2025-05-29T03:40:21Z","abstract_excerpt":"Recent advancements in unified vision-language models (VLMs), which integrate both visual understanding and generation capabilities, have attracted significant attention. The underlying hypothesis is that a unified architecture with mixed training on both understanding and generation tasks can enable mutual enhancement between understanding and generation. However, this hypothesis remains underexplored in prior works on unified VLMs. To address this gap, this paper systematically investigates the generalization across understanding and generation tasks in unified VLMs. Specifically, we design "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23043","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/2505.23043/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":"2026-07-05T11:11:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1QFF9aghtOAPq7MD6TzjN27mSv2yovuTt64tMM16/uHLY+BzRL5Jau62QxQiumBPcqIRYHlwBqzKJ/ciaXCeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:38:59.547866Z"},"content_sha256":"71fd38610eae7aa9f8b4411f6f1f3e0552f67a6e2addef98184a72351e30492c","schema_version":"1.0","event_id":"sha256:71fd38610eae7aa9f8b4411f6f1f3e0552f67a6e2addef98184a72351e30492c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EN5VB2LH42MWDRG7777COSEXVR/bundle.json","state_url":"https://pith.science/pith/EN5VB2LH42MWDRG7777COSEXVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EN5VB2LH42MWDRG7777COSEXVR/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":"2026-08-05T06:38:59Z","links":{"resolver":"https://pith.science/pith/EN5VB2LH42MWDRG7777COSEXVR","bundle":"https://pith.science/pith/EN5VB2LH42MWDRG7777COSEXVR/bundle.json","state":"https://pith.science/pith/EN5VB2LH42MWDRG7777COSEXVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EN5VB2LH42MWDRG7777COSEXVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EN5VB2LH42MWDRG7777COSEXVR","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":"63a374a03e492d3310f61c10cda0cffeda36eadac3a2ed8ab35e8f9ff7933a51","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:40:21Z","title_canon_sha256":"ed286186d62cfcb27dd49215a0a8d686e68c42ddfefc7c11aadc9dcf6185378d"},"schema_version":"1.0","source":{"id":"2505.23043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23043","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23043v1","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23043","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_12","alias_value":"EN5VB2LH42MW","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_16","alias_value":"EN5VB2LH42MWDRG7","created_at":"2026-07-05T11:11:54Z"},{"alias_kind":"pith_short_8","alias_value":"EN5VB2LH","created_at":"2026-07-05T11:11:54Z"}],"graph_snapshots":[{"event_id":"sha256:71fd38610eae7aa9f8b4411f6f1f3e0552f67a6e2addef98184a72351e30492c","target":"graph","created_at":"2026-07-05T11:11:54Z","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/2505.23043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in unified vision-language models (VLMs), which integrate both visual understanding and generation capabilities, have attracted significant attention. The underlying hypothesis is that a unified architecture with mixed training on both understanding and generation tasks can enable mutual enhancement between understanding and generation. However, this hypothesis remains underexplored in prior works on unified VLMs. To address this gap, this paper systematically investigates the generalization across understanding and generation tasks in unified VLMs. Specifically, we design ","authors_text":"Jihai Zhang, Linjie Li, Tianle Li, Yu Cheng, Zhengyuan Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:40:21Z","title":"Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23043","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":"sha256:8e57b9673e11252d3517ea5a10d4d12198283f1ea9509518f450be1b6135664b","target":"record","created_at":"2026-07-05T11:11:54Z","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":"63a374a03e492d3310f61c10cda0cffeda36eadac3a2ed8ab35e8f9ff7933a51","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T03:40:21Z","title_canon_sha256":"ed286186d62cfcb27dd49215a0a8d686e68c42ddfefc7c11aadc9dcf6185378d"},"schema_version":"1.0","source":{"id":"2505.23043","kind":"arxiv","version":1}},"canonical_sha256":"237b50e967e69961c4dffffe274897ac48470193cdc9dfb06668b47148b2bf88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"237b50e967e69961c4dffffe274897ac48470193cdc9dfb06668b47148b2bf88","first_computed_at":"2026-07-05T11:11:54.252143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:54.252143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eGiGRto+d2wSn40vIzmWBRDzr9SojhLIuW/iFJsksxLeycYIH8+0aIVea+1Vd6bPJoTBjDSp/y8nsd09OmR0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:54.252696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e57b9673e11252d3517ea5a10d4d12198283f1ea9509518f450be1b6135664b","sha256:71fd38610eae7aa9f8b4411f6f1f3e0552f67a6e2addef98184a72351e30492c"],"state_sha256":"bd9becc04749ad66963372dd8d1c9b134205af720cbbc3d5478bcf94a6943fcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HLU8XMjG1sud9UX8XsoUncg2vdhwGpoKXuB0LCBUc/FDWeYTP68NwLJ+jFREYsMwDgkQ4R0k3eU6g33x7kmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:38:59.554565Z","bundle_sha256":"97d8162c0faba8e04f23724c2d729b11b7db1b8b81323f4daf65ddfdd878fa3b"}}