{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SIQHW4DN2AELULETGUEFPJMCEA","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":"77f638d311c4742ec0b5398505cdc4b363cf566080f12fc38d395c8d29d0312c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T16:33:32Z","title_canon_sha256":"7a0caf5e69399bfaec971962e2b90613b30e6b5727469e972fc53a1d1abf6749"},"schema_version":"1.0","source":{"id":"2312.17109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17109","created_at":"2026-07-05T07:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17109v1","created_at":"2026-07-05T07:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17109","created_at":"2026-07-05T07:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"SIQHW4DN2AEL","created_at":"2026-07-05T07:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"SIQHW4DN2AELULET","created_at":"2026-07-05T07:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"SIQHW4DN","created_at":"2026-07-05T07:28:39Z"}],"graph_snapshots":[{"event_id":"sha256:4bd150d7e5c583afde5d81abc1c61d8ea83e8d7976faf2d51953ba5f7ea31ba4","target":"graph","created_at":"2026-07-05T07:28:39Z","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/2312.17109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models have been widely explored across a wide range of tasks and achieve satisfactory performance. However, it's under-explored how to consolidate entity understanding through a varying number of images and to align it with the pre-trained language models for generative tasks. In this paper, we propose MIVC, a general multiple instance visual component to bridge the gap between various image inputs with off-the-shelf vision-language models by aggregating visual representations in a permutation-invariant fashion through a neural network. We show that MIVC could be plugged into ","authors_text":"Junzhou Huang, Qi Li, Wenliang Zhong, Wenyi Wu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T16:33:32Z","title":"MIVC: Multiple Instance Visual Component for Visual-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17109","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":"sha256:6bb379ccd90feebb959d3002227e55f0c491692fea3d4f9ceff4dccc61701b3e","target":"record","created_at":"2026-07-05T07:28:39Z","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":"77f638d311c4742ec0b5398505cdc4b363cf566080f12fc38d395c8d29d0312c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T16:33:32Z","title_canon_sha256":"7a0caf5e69399bfaec971962e2b90613b30e6b5727469e972fc53a1d1abf6749"},"schema_version":"1.0","source":{"id":"2312.17109","kind":"arxiv","version":1}},"canonical_sha256":"92207b706dd008ba2c93350857a582200bdf76882d19ba785f105800620bc892","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92207b706dd008ba2c93350857a582200bdf76882d19ba785f105800620bc892","first_computed_at":"2026-07-05T07:28:39.791099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:39.791099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l1p46+reOBWNyD6gXwddQCfQRhy3shTExouvZvAN7EVKGsJLfcuGkGoJ903kie4Syq6qoM8+gKMom5odaPBGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:39.791717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bb379ccd90feebb959d3002227e55f0c491692fea3d4f9ceff4dccc61701b3e","sha256:4bd150d7e5c583afde5d81abc1c61d8ea83e8d7976faf2d51953ba5f7ea31ba4"],"state_sha256":"3a17e817ef9b7aff7a73d2f3ac7d76cd41b212ce5406966e583063aa0116b242"}