{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UWDYL5OXYIJGNUTAHAROKRB5II","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":"3759a375a50aa14c807db0dd24acfa4db7c0e8f23a80251f8848d1290627a8ba","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T22:45:13Z","title_canon_sha256":"3c834d624c6a73ed5f6e5741defe9924d09c65f37945d6e9b2246e11bc6e9645"},"schema_version":"1.0","source":{"id":"2410.14072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14072","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14072v1","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14072","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_12","alias_value":"UWDYL5OXYIJG","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_16","alias_value":"UWDYL5OXYIJGNUTA","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_8","alias_value":"UWDYL5OX","created_at":"2026-07-05T09:22:26Z"}],"graph_snapshots":[{"event_id":"sha256:739ae3cffe054635e3988818b2c7032f03af9ad71ac3a89287d637afa037e62f","target":"graph","created_at":"2026-07-05T09:22:26Z","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/2410.14072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the widely used fully autoregressive transformer-based models like LLaVA, projected visual tokens are prepended to textual tokens. Oftentimes, visual tokens are significantly more than prompt tokens, resulting in increased computational overhead during both training and inference. In this paper, we propose Visual Compact Token Registers (Victor), a method that reduces the number of visual tokens by summarizing them into","authors_text":"Mahyar Najibi, Qichen Fu, Qingqing Cao, Sachin Mehta, Yuxin Wen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T22:45:13Z","title":"Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14072","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:a9589b3ba04c8fbe447204ee5977b16509b44207203fda03054a2aba571d95a4","target":"record","created_at":"2026-07-05T09:22:26Z","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":"3759a375a50aa14c807db0dd24acfa4db7c0e8f23a80251f8848d1290627a8ba","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T22:45:13Z","title_canon_sha256":"3c834d624c6a73ed5f6e5741defe9924d09c65f37945d6e9b2246e11bc6e9645"},"schema_version":"1.0","source":{"id":"2410.14072","kind":"arxiv","version":1}},"canonical_sha256":"a58785f5d7c21266d2603822e5443d42350d156f633a532e36b06672b6ace19f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a58785f5d7c21266d2603822e5443d42350d156f633a532e36b06672b6ace19f","first_computed_at":"2026-07-05T09:22:26.710049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:26.710049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1zbnBIOzE5YiAuAzwJAFGMtYSuK7fO277SaxxMud7K5J9yMfVqytq3I5St9ltDZQMVGEMlAInfJY817iXFA1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:26.710624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9589b3ba04c8fbe447204ee5977b16509b44207203fda03054a2aba571d95a4","sha256:739ae3cffe054635e3988818b2c7032f03af9ad71ac3a89287d637afa037e62f"],"state_sha256":"7f647a02d6094ecb1749956713690f24d0bc5c17c349abe5cd7195ebf6d12a48"}