{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3CN76X7SL7BWBRR7TNHCCCHUEH","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":"e09d89047feb40b5c98e893cf4613b6920882123662d986373d6d0623b2fd6a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-21T06:13:56Z","title_canon_sha256":"709190b2114af50e4ed0ba75aa61ebaf0fa7a26fcc2eb5b1164e72dc0dbcd678"},"schema_version":"1.0","source":{"id":"2506.17608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17608","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17608v1","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17608","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"pith_short_12","alias_value":"3CN76X7SL7BW","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"pith_short_16","alias_value":"3CN76X7SL7BWBRR7","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"pith_short_8","alias_value":"3CN76X7S","created_at":"2026-07-05T11:25:20Z"}],"graph_snapshots":[{"event_id":"sha256:dc0ee0b9a7ae457915b87e2856edf0c6f3458d7e7efc6b04bb40ecd776591723","target":"graph","created_at":"2026-07-05T11:25:20Z","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/2506.17608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of high-resolution image features in modern multimodal large language models has demonstrated significant improvements in fine-grained visual understanding tasks, achieving high performance across multiple benchmarks. Since these features are obtained from large image encoders like ViT, they come with a significant increase in computational costs due to multiple calls to these encoders. In this work, we first develop an intuition for feature upsampling as a natural extension of high-resolution feature generation. Through extensive experiments and ablations, we demonstrate how a","authors_text":"Aradhya Neeraj Mathur, Mausoom Sarkar, Nikitha SR, Rishabh Jain, Tarun Ram Menta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-21T06:13:56Z","title":"HIRE: Lightweight High-Resolution Image Feature Enrichment for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17608","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":"sha256:05f6a4300b95cd3bea5acc3beeab80f6f7c124a8e89a48b90b6abc4883011e99","target":"record","created_at":"2026-07-05T11:25:20Z","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":"e09d89047feb40b5c98e893cf4613b6920882123662d986373d6d0623b2fd6a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-21T06:13:56Z","title_canon_sha256":"709190b2114af50e4ed0ba75aa61ebaf0fa7a26fcc2eb5b1164e72dc0dbcd678"},"schema_version":"1.0","source":{"id":"2506.17608","kind":"arxiv","version":1}},"canonical_sha256":"d89bff5ff25fc360c63f9b4e2108f421d96c0dfb45b6eb8c1046395ef5a53ba3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d89bff5ff25fc360c63f9b4e2108f421d96c0dfb45b6eb8c1046395ef5a53ba3","first_computed_at":"2026-07-05T11:25:20.366702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:20.366702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oEXQROtSlCoqn3oss9eyBxQjS9DVezgQq8A5uDfczMqBoV2g51NKmWn+LnhBoGu+9za/AB9vmn8ZVqNWklemBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:20.367173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f6a4300b95cd3bea5acc3beeab80f6f7c124a8e89a48b90b6abc4883011e99","sha256:dc0ee0b9a7ae457915b87e2856edf0c6f3458d7e7efc6b04bb40ecd776591723"],"state_sha256":"2c37abf1fa50af24f052d79f4ea5bcc50c822bb5c41ca4507e1b056fe7e469ff"}