{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XXDN7WI3DNRCXG5JEMEUT2COCC","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":"105d840a961614c1ee65b89452beab2a246ca4054566503331e43a990c431773","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T14:00:59Z","title_canon_sha256":"453d23e096df40ff3af5ed05e1991cfd4562df681d266a861ad26d15f6333cc4"},"schema_version":"1.0","source":{"id":"2503.04444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04444","created_at":"2026-07-05T10:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04444v1","created_at":"2026-07-05T10:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04444","created_at":"2026-07-05T10:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"XXDN7WI3DNRC","created_at":"2026-07-05T10:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"XXDN7WI3DNRCXG5J","created_at":"2026-07-05T10:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"XXDN7WI3","created_at":"2026-07-05T10:25:38Z"}],"graph_snapshots":[{"event_id":"sha256:fea76d58fd1c40b110f226e34ea6a78b1b88333d78c750934dcb9fa4adc5fa85","target":"graph","created_at":"2026-07-05T10:25:38Z","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/2503.04444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) are powerful tools that are capable of reasoning and understanding multimodal information beyond text and language. Despite their entrenched impact, the development of LMMs is hindered by the higher computational requirements compared to their unimodal counterparts. One of the main causes of this is the large amount of tokens needed to encode the visual input, which is especially evident for multi-image multimodal tasks. Recent approaches to reduce visual tokens depend on the visual encoder architecture, require fine-tuning the LLM to maintain the performance, an","authors_text":"Loris Bazzani, Matthieu Guillaumin, Maximilian Jaritz, Rita Cucchiara, Silvia Cascianelli, Vittorio Pippi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T14:00:59Z","title":"ToFu: Visual Tokens Reduction via Fusion for Multi-modal, Multi-patch, Multi-image Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04444","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":"sha256:7037b3ac0fc3ab50738a667419c1df9b1d31705dca6e79ff0c87d57c337e5686","target":"record","created_at":"2026-07-05T10:25:38Z","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":"105d840a961614c1ee65b89452beab2a246ca4054566503331e43a990c431773","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T14:00:59Z","title_canon_sha256":"453d23e096df40ff3af5ed05e1991cfd4562df681d266a861ad26d15f6333cc4"},"schema_version":"1.0","source":{"id":"2503.04444","kind":"arxiv","version":1}},"canonical_sha256":"bdc6dfd91b1b622b9ba9230949e84e1099a344b8776784d9cb01c05c43817d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdc6dfd91b1b622b9ba9230949e84e1099a344b8776784d9cb01c05c43817d45","first_computed_at":"2026-07-05T10:25:38.713007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:38.713007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MKQxMl7RfVF2rpqSZaya3V1TJOCL4FnEbprYxb/FzIx1RZ+zcHwqUFTMBful/6CFWZJpDTK5738xbWHSNkLxAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:38.713579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7037b3ac0fc3ab50738a667419c1df9b1d31705dca6e79ff0c87d57c337e5686","sha256:fea76d58fd1c40b110f226e34ea6a78b1b88333d78c750934dcb9fa4adc5fa85"],"state_sha256":"97247d575a80913905fbaf4e21a2b5e0666ac5a1d5d58b7b23c964fe73127654"}