{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TZUZZSOB6HOOB4IFZPWHEONVFW","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":"1106b5cd75688ae98b0ce26b4a2f6affdedbb21b34404be8f0c486882bfa411b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T06:48:46Z","title_canon_sha256":"ce40b0f7e6c9d52450241dc9ae0d9032bb20a3050ad0f18048d83b9c83edda7e"},"schema_version":"1.0","source":{"id":"2408.12867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12867","created_at":"2026-07-05T08:58:31Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12867v1","created_at":"2026-07-05T08:58:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12867","created_at":"2026-07-05T08:58:31Z"},{"alias_kind":"pith_short_12","alias_value":"TZUZZSOB6HOO","created_at":"2026-07-05T08:58:31Z"},{"alias_kind":"pith_short_16","alias_value":"TZUZZSOB6HOOB4IF","created_at":"2026-07-05T08:58:31Z"},{"alias_kind":"pith_short_8","alias_value":"TZUZZSOB","created_at":"2026-07-05T08:58:31Z"}],"graph_snapshots":[{"event_id":"sha256:414d88219d8379590d86e9f65b288851be5c68066a49d500ea3223971ffd2124","target":"graph","created_at":"2026-07-05T08:58:31Z","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/2408.12867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g., change captioning). Existing MLLMs typically follow a two-step process in their pipelines: first, extracting visual tokens independently for each input image, and then aligning these visual tokens from different images with the Large Language Model (LLM) in its textual feature space. However, the independent extraction of visual tokens for each image may result ","authors_text":"Fei Wu, Jingyuan Chen, Jinyang Gao, Kun Kuang, Mengze Li, Tao Wu, Wang Lin, Wei Ji, Zhou Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T06:48:46Z","title":"Semantic Alignment for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12867","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":"sha256:8cc73e1a72675c917d9a8fd408d3ced1a3f05d2b030aca5eee39e8a2064bdaeb","target":"record","created_at":"2026-07-05T08:58:31Z","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":"1106b5cd75688ae98b0ce26b4a2f6affdedbb21b34404be8f0c486882bfa411b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T06:48:46Z","title_canon_sha256":"ce40b0f7e6c9d52450241dc9ae0d9032bb20a3050ad0f18048d83b9c83edda7e"},"schema_version":"1.0","source":{"id":"2408.12867","kind":"arxiv","version":1}},"canonical_sha256":"9e699cc9c1f1dce0f105cbec7239b52dab093ede55f43fb19ad9a0aa99f7d22a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e699cc9c1f1dce0f105cbec7239b52dab093ede55f43fb19ad9a0aa99f7d22a","first_computed_at":"2026-07-05T08:58:31.838253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:31.838253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IVRtEszaZ1FKYkk43SDugoy/zxIJC0eR+lkH8i7Onb61x4BqDBxH7zDq777DnCIE0kGu7+LojQLm5ivOtlLTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:31.838741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cc73e1a72675c917d9a8fd408d3ced1a3f05d2b030aca5eee39e8a2064bdaeb","sha256:414d88219d8379590d86e9f65b288851be5c68066a49d500ea3223971ffd2124"],"state_sha256":"24674d59f68776976849f7d0720ab4b86541d9662f680cbe4b9ef149051ec431"}