{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6QEFIVEWQSH3DD27Z24UZ5VDNM","short_pith_number":"pith:6QEFIVEW","canonical_record":{"source":{"id":"2503.06542","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T10:15:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e2cf1bfc49f9aa0a09b0b2827907d9748b2215d3792c3bf7cbb1c3ba8cebbcc","abstract_canon_sha256":"6855a0a14d3b68d2558fb28b1df3b7e66c65186fe6d00231d0286de2ccedebef"},"schema_version":"1.0"},"canonical_sha256":"f408545496848fb18f5fceb94cf6a36b21d78a3a0cc75012ae33cff93fb24af3","source":{"kind":"arxiv","id":"2503.06542","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06542","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06542v2","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06542","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_12","alias_value":"6QEFIVEWQSH3","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_16","alias_value":"6QEFIVEWQSH3DD27","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_8","alias_value":"6QEFIVEW","created_at":"2026-07-05T11:17:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6QEFIVEWQSH3DD27Z24UZ5VDNM","target":"record","payload":{"canonical_record":{"source":{"id":"2503.06542","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T10:15:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e2cf1bfc49f9aa0a09b0b2827907d9748b2215d3792c3bf7cbb1c3ba8cebbcc","abstract_canon_sha256":"6855a0a14d3b68d2558fb28b1df3b7e66c65186fe6d00231d0286de2ccedebef"},"schema_version":"1.0"},"canonical_sha256":"f408545496848fb18f5fceb94cf6a36b21d78a3a0cc75012ae33cff93fb24af3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:23.813556Z","signature_b64":"gvFk53IsVEDqgH1e6S3aBTYlQxBY661frLzYE83EOB8ouaG8iKe2+ncq0WW/D6Acmlk96nZOrbOo3JlMyzXiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f408545496848fb18f5fceb94cf6a36b21d78a3a0cc75012ae33cff93fb24af3","last_reissued_at":"2026-07-05T11:17:23.813041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:23.813041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.06542","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQgPyBIn94839pqfRf+x3/b2Vb5CIaI5me/UJ6EcPRupvGMC3gvArQEHJI295S2s/w3l7jiZvp+I2beVN3AgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:38:04.935042Z"},"content_sha256":"04e8e069c584b32dddf49c246dbf2ca5bad79d71fc6de0e61abb9ac7782b490e","schema_version":"1.0","event_id":"sha256:04e8e069c584b32dddf49c246dbf2ca5bad79d71fc6de0e61abb9ac7782b490e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6QEFIVEWQSH3DD27Z24UZ5VDNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Fanrui Zhang, Jianwen Sun, Jiaxin Ai, Kaipeng Zhang, Shenglin Zhang, Sizhuo Zhou, Yu Dai, Yukang Feng, Zizhen Li","submitted_at":"2025-03-09T10:15:39Z","abstract_excerpt":"Unified multimodal understanding and generation have recently received much attention in the area of vision and language. Existing UniMs are designed to simultaneously learn both multimodal understanding and generation capabilities, demanding substantial computational resources, and often struggle to generate interleaved text-image. We present ARMOR, a resource-efficient and pure autoregressive framework that achieves both understanding and generation by fine-tuning existing multimodal large language models (MLLMs). Specifically, ARMOR extends existing MLLMs from three perspectives: (1) For mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06542","kind":"arxiv","version":2},"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/2503.06542/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":"2026-07-05T11:17:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUeM5Nuqq8teJ/kf0S7l9KjY0PNE3Kbnq8xOyOYqjUFAqWQbGGHHG6XGHgigmEkjSBVffH8MeQyGaQCPxzXsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:38:04.935586Z"},"content_sha256":"eaec0c315fd114c69fd0f334f3ad39aff4bdda40d96b48f657a5dbb8daafe501","schema_version":"1.0","event_id":"sha256:eaec0c315fd114c69fd0f334f3ad39aff4bdda40d96b48f657a5dbb8daafe501"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6QEFIVEWQSH3DD27Z24UZ5VDNM/bundle.json","state_url":"https://pith.science/pith/6QEFIVEWQSH3DD27Z24UZ5VDNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6QEFIVEWQSH3DD27Z24UZ5VDNM/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":"2026-08-03T15:38:04Z","links":{"resolver":"https://pith.science/pith/6QEFIVEWQSH3DD27Z24UZ5VDNM","bundle":"https://pith.science/pith/6QEFIVEWQSH3DD27Z24UZ5VDNM/bundle.json","state":"https://pith.science/pith/6QEFIVEWQSH3DD27Z24UZ5VDNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6QEFIVEWQSH3DD27Z24UZ5VDNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6QEFIVEWQSH3DD27Z24UZ5VDNM","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":"6855a0a14d3b68d2558fb28b1df3b7e66c65186fe6d00231d0286de2ccedebef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T10:15:39Z","title_canon_sha256":"0e2cf1bfc49f9aa0a09b0b2827907d9748b2215d3792c3bf7cbb1c3ba8cebbcc"},"schema_version":"1.0","source":{"id":"2503.06542","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06542","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06542v2","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06542","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_12","alias_value":"6QEFIVEWQSH3","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_16","alias_value":"6QEFIVEWQSH3DD27","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_8","alias_value":"6QEFIVEW","created_at":"2026-07-05T11:17:23Z"}],"graph_snapshots":[{"event_id":"sha256:eaec0c315fd114c69fd0f334f3ad39aff4bdda40d96b48f657a5dbb8daafe501","target":"graph","created_at":"2026-07-05T11:17:23Z","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/2503.06542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified multimodal understanding and generation have recently received much attention in the area of vision and language. Existing UniMs are designed to simultaneously learn both multimodal understanding and generation capabilities, demanding substantial computational resources, and often struggle to generate interleaved text-image. We present ARMOR, a resource-efficient and pure autoregressive framework that achieves both understanding and generation by fine-tuning existing multimodal large language models (MLLMs). Specifically, ARMOR extends existing MLLMs from three perspectives: (1) For mo","authors_text":"Chuanhao Li, Fanrui Zhang, Jianwen Sun, Jiaxin Ai, Kaipeng Zhang, Shenglin Zhang, Sizhuo Zhou, Yu Dai, Yukang Feng, Zizhen Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T10:15:39Z","title":"ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06542","kind":"arxiv","version":2},"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":"sha256:04e8e069c584b32dddf49c246dbf2ca5bad79d71fc6de0e61abb9ac7782b490e","target":"record","created_at":"2026-07-05T11:17:23Z","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":"6855a0a14d3b68d2558fb28b1df3b7e66c65186fe6d00231d0286de2ccedebef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T10:15:39Z","title_canon_sha256":"0e2cf1bfc49f9aa0a09b0b2827907d9748b2215d3792c3bf7cbb1c3ba8cebbcc"},"schema_version":"1.0","source":{"id":"2503.06542","kind":"arxiv","version":2}},"canonical_sha256":"f408545496848fb18f5fceb94cf6a36b21d78a3a0cc75012ae33cff93fb24af3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f408545496848fb18f5fceb94cf6a36b21d78a3a0cc75012ae33cff93fb24af3","first_computed_at":"2026-07-05T11:17:23.813041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:23.813041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gvFk53IsVEDqgH1e6S3aBTYlQxBY661frLzYE83EOB8ouaG8iKe2+ncq0WW/D6Acmlk96nZOrbOo3JlMyzXiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:23.813556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06542","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04e8e069c584b32dddf49c246dbf2ca5bad79d71fc6de0e61abb9ac7782b490e","sha256:eaec0c315fd114c69fd0f334f3ad39aff4bdda40d96b48f657a5dbb8daafe501"],"state_sha256":"eacbb1f6f3a77733ed1afe7e38fdc8cff5fcb92c683b44cbaba7a618da370436"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ro9eyvAxwqTB+XoxmfB1u2CDUuHtdISitfPH3HtfYYuaCQ9RvDPKhx9PHSQydC9Mk0VPKaK6ntzk25L41L+JBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:38:04.941913Z","bundle_sha256":"f3f07d3fcc41a2875c57e88524358f63ffb17723c443259740e550bbd835edb2"}}