{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JJMXHVWZ2O62D2TRWMHCTGYZBN","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":"af478cfcaeefa9cc3a944b03f9338b4ec6dfd9334d454ec0c69192fe6209400c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T09:11:50Z","title_canon_sha256":"fc0cc9c40e556c0afa01328c522aff907c05766674c92836c11932c50f8ab401"},"schema_version":"1.0","source":{"id":"2606.31383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31383","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31383v1","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31383","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"JJMXHVWZ2O62","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"JJMXHVWZ2O62D2TR","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"JJMXHVWZ","created_at":"2026-07-01T01:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:d77162122856080114d551df66c8850c17dc3568bb6ad2f03c90d7f90824dc10","target":"graph","created_at":"2026-07-01T01:18:01Z","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/2606.31383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform dense visual features into a compact token sequence for language modeling. Most existing resamplers adopt a single, fixed aggregation scope via global cross-attention, which can blur fine-grained local evidence and limit the ability to capture both local details and global context within a fixed token budget. In this work, we propose MS-Resampler, a multi-scope visual resampling framework for MLLMs. MS-Resampler instantiates multiple scope-specific resamplers by injecting explicit spatial scope p","authors_text":"Cheng Qian, Faming Fang, Guixu Zhang, Kaiwen Long, Mo Guang, Rinyoichi Takezoe, Yaqian Li, Zhongyang Li, Zi-Hao Bo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T09:11:50Z","title":"MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31383","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":"sha256:5a2452e7d18480dee56ddd5251de32bce5ad628ae32e815ff18db8ae599f483b","target":"record","created_at":"2026-07-01T01:18:01Z","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":"af478cfcaeefa9cc3a944b03f9338b4ec6dfd9334d454ec0c69192fe6209400c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T09:11:50Z","title_canon_sha256":"fc0cc9c40e556c0afa01328c522aff907c05766674c92836c11932c50f8ab401"},"schema_version":"1.0","source":{"id":"2606.31383","kind":"arxiv","version":1}},"canonical_sha256":"4a5973d6d9d3bda1ea71b30e299b190b622520635d27f7b287bb62d6040a9b87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a5973d6d9d3bda1ea71b30e299b190b622520635d27f7b287bb62d6040a9b87","first_computed_at":"2026-07-01T01:18:01.440082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:01.440082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hfXR5inIfgU8fO1yUC8gViXdx9ax6s1Mjt7dc643YmZZqfIrXR1Ofkw1C7cYCNYfpDvHgkfUdTrNlHixQMVEBg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:01.440519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a2452e7d18480dee56ddd5251de32bce5ad628ae32e815ff18db8ae599f483b","sha256:d77162122856080114d551df66c8850c17dc3568bb6ad2f03c90d7f90824dc10"],"state_sha256":"366255e369512c5f891b8017f4ee0aa06ff63411cdc5632a45f2a22b38659f76"}