{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P7VNWM6BU6YIND4JFRYYASXHPL","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":"3339bb026c328f40d780a25d6cd7720439715812ad6bbe49bc51f0a110391809","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:59:06Z","title_canon_sha256":"f07b413fae7416e52a7b13530a058496ad50fcb0f089e93257768289efaf21e1"},"schema_version":"1.0","source":{"id":"2312.06742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06742","created_at":"2026-07-05T08:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06742v2","created_at":"2026-07-05T08:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06742","created_at":"2026-07-05T08:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"P7VNWM6BU6YI","created_at":"2026-07-05T08:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"P7VNWM6BU6YIND4J","created_at":"2026-07-05T08:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"P7VNWM6B","created_at":"2026-07-05T08:02:49Z"}],"graph_snapshots":[{"event_id":"sha256:f0b132f6a8c2d2aed1759271cc1a4189338ae35e233c19d59defb1395697b7e3","target":"graph","created_at":"2026-07-05T08:02:49Z","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/2312.06742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Multimodal Large Language Models (MLLMs), a visual projector plays a crucial role in bridging pre-trained vision encoders with LLMs, enabling profound visual understanding while harnessing the LLMs' robust capabilities. Despite the importance of the visual projector, it has been relatively less explored. In this study, we first identify two essential projector properties: (i) flexibility in managing the number of visual tokens, crucial for MLLMs' overall efficiency, and (ii) preservation of local context from visual features, vital for spatial understanding. Based on these findings, we prop","authors_text":"Byungseok Roh, Jonghwan Mun, Junbum Cha, Wooyoung Kang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:59:06Z","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06742","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:c58d6a87ecede2fe73595256658f9f1f35047aeab230cd92649b777853203f74","target":"record","created_at":"2026-07-05T08:02:49Z","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":"3339bb026c328f40d780a25d6cd7720439715812ad6bbe49bc51f0a110391809","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:59:06Z","title_canon_sha256":"f07b413fae7416e52a7b13530a058496ad50fcb0f089e93257768289efaf21e1"},"schema_version":"1.0","source":{"id":"2312.06742","kind":"arxiv","version":2}},"canonical_sha256":"7feadb33c1a7b0868f892c71804ae77afcf9da4f6cf3dac039874b611df65361","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7feadb33c1a7b0868f892c71804ae77afcf9da4f6cf3dac039874b611df65361","first_computed_at":"2026-07-05T08:02:49.172423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:49.172423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/q77tLmYsvtcN/NSRbtQ32W0XwC1d+PgGhmO5Bx3y4WuGfKfTnOO8lc4/JbfdgtlUTMxpWT1lHL87WKSy7MtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:49.172902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c58d6a87ecede2fe73595256658f9f1f35047aeab230cd92649b777853203f74","sha256:f0b132f6a8c2d2aed1759271cc1a4189338ae35e233c19d59defb1395697b7e3"],"state_sha256":"88da633a3544bcfba198bbe60f43a76ad5046eba336066eb3ea537b755bbc0ab"}