{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2N2QR6MK2ULTIASXN6PQF56JO5","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":"efd79d300815d87a06f5d188a1e67ce26137d1a819afbb0e5ebf1abe27a83967","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T08:43:06Z","title_canon_sha256":"3f09e1dead4a67102e1409b49df6fe8a34ab23b94049ddc549cad595890a3172"},"schema_version":"1.0","source":{"id":"2405.01926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01926","created_at":"2026-07-05T08:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01926v1","created_at":"2026-07-05T08:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01926","created_at":"2026-07-05T08:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"2N2QR6MK2ULT","created_at":"2026-07-05T08:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"2N2QR6MK2ULTIASX","created_at":"2026-07-05T08:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"2N2QR6MK","created_at":"2026-07-05T08:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:4cc5a061f778fc1190b6e2830fdcbacd3287ea56a1e2d8abe68344c8033ccfbd","target":"graph","created_at":"2026-07-05T08:15:04Z","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/2405.01926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For multimodal LLMs, the synergy of visual comprehension (textual output) and generation (visual output) presents an ongoing challenge. This is due to a conflicting objective: for comprehension, an MLLM needs to abstract the visuals; for generation, it needs to preserve the visuals as much as possible. Thus, the objective is a dilemma for visual-tokens. To resolve the conflict, we propose encoding images into morph-tokens to serve a dual purpose: for comprehension, they act as visual prompts instructing MLLM to generate texts; for generation, they take on a different, non-conflicting role as c","authors_text":"Hanwang Zhang, Juncheng Li, Kaihang Pan, Shuicheng Yan, Siliang Tang, Tat-Seng Chua, Wei Chow, Yueting Zhuang, Zhaoyu Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T08:43:06Z","title":"Auto-Encoding Morph-Tokens for Multimodal LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01926","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":"sha256:30260641bbeaaffa0173c00a440de42ea890e5e21b390b7bbb7d11be44508e75","target":"record","created_at":"2026-07-05T08:15:04Z","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":"efd79d300815d87a06f5d188a1e67ce26137d1a819afbb0e5ebf1abe27a83967","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T08:43:06Z","title_canon_sha256":"3f09e1dead4a67102e1409b49df6fe8a34ab23b94049ddc549cad595890a3172"},"schema_version":"1.0","source":{"id":"2405.01926","kind":"arxiv","version":1}},"canonical_sha256":"d37508f98ad5173402576f9f02f7c9774f33f73b6a0ffb23ffa4693e64c6071f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d37508f98ad5173402576f9f02f7c9774f33f73b6a0ffb23ffa4693e64c6071f","first_computed_at":"2026-07-05T08:15:04.388327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:04.388327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZNIEoA3zibbPyvOfO1LkSQ8XP9ZJsiYfLyo+v29APTA8zQ28laOnG9NoqXnHQTKrbDwrdxyFGngDclOJpy2fDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:04.388773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30260641bbeaaffa0173c00a440de42ea890e5e21b390b7bbb7d11be44508e75","sha256:4cc5a061f778fc1190b6e2830fdcbacd3287ea56a1e2d8abe68344c8033ccfbd"],"state_sha256":"a7ae9710b843835256343131e2b7d2bb6f5865de6b97eda6e609cc3792e43e2c"}