{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IXX6HMK55IVNKWI3HJL6OQUFRT","short_pith_number":"pith:IXX6HMK5","canonical_record":{"source":{"id":"2607.28627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:59:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6182e7cd3bf959f244fd773d5f24d20464aa260b185ed4d690e57ad3b628a19e","abstract_canon_sha256":"f942798d38e121512ae34c76a87d72e8644ca5502ff966d54639127664b20fc7"},"schema_version":"1.0"},"canonical_sha256":"45efe3b15dea2ad5591b3a57e742858ce2dcd9bac6a7aa6d50ddc1c50b497a98","source":{"kind":"arxiv","id":"2607.28627","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28627","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28627v1","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28627","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"IXX6HMK55IVN","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"pith_short_16","alias_value":"IXX6HMK55IVNKWI3","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"pith_short_8","alias_value":"IXX6HMK5","created_at":"2026-07-31T01:39:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IXX6HMK55IVNKWI3HJL6OQUFRT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:59:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6182e7cd3bf959f244fd773d5f24d20464aa260b185ed4d690e57ad3b628a19e","abstract_canon_sha256":"f942798d38e121512ae34c76a87d72e8644ca5502ff966d54639127664b20fc7"},"schema_version":"1.0"},"canonical_sha256":"45efe3b15dea2ad5591b3a57e742858ce2dcd9bac6a7aa6d50ddc1c50b497a98","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45efe3b15dea2ad5591b3a57e742858ce2dcd9bac6a7aa6d50ddc1c50b497a98","last_reissued_at":"2026-07-31T01:39:09.180132Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:39:09.180132Z"},"source_kind":"arxiv","source_id":"2607.28627","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OlwM78u5uIHOrWpfSiWMLbpReCtaRRv0JvRVu61UdW0YJ+IHASah98FRyoCZgVIFUuqBZmJANW1EtQqykFNVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:40:30.804595Z"},"content_sha256":"1436ab4c59e3d72c620b33b0ef00f6c02553ca45b807129ffa467135af2c4faf","schema_version":"1.0","event_id":"sha256:1436ab4c59e3d72c620b33b0ef00f6c02553ca45b807129ffa467135af2c4faf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IXX6HMK55IVNKWI3HJL6OQUFRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReToken: One Token to Improve Vision-Language Models for Visual Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Derek Hoiem, Jianfeng Gao, Reuben Tan, Yao Xiao, Yuqun Wu, Zhen Zhu","submitted_at":"2026-07-30T17:59:56Z","abstract_excerpt":"Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints. We present ReToken, a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache. Trained on only a small image-QA dataset, ReToken yields consistent gains across image and video benchmarks: on Visual Haystacks it improves Qwen3VL-8B by 13.4 points and InternVL3.5 by 12.4 points (>2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28627","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.28627/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4lkrfruaxwkQooniKYAvhPftuq6rEvbF+IjPTYJyxr2Tp/jEarE/ScLrSVhwcXoh5LQXRrwcvgCHNtQvQQHDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:40:30.805149Z"},"content_sha256":"651f30159ebc4087b06c7315389d3ff9cf977d29a275c38836404cbe7d1445aa","schema_version":"1.0","event_id":"sha256:651f30159ebc4087b06c7315389d3ff9cf977d29a275c38836404cbe7d1445aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXX6HMK55IVNKWI3HJL6OQUFRT/bundle.json","state_url":"https://pith.science/pith/IXX6HMK55IVNKWI3HJL6OQUFRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXX6HMK55IVNKWI3HJL6OQUFRT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T04:40:30Z","links":{"resolver":"https://pith.science/pith/IXX6HMK55IVNKWI3HJL6OQUFRT","bundle":"https://pith.science/pith/IXX6HMK55IVNKWI3HJL6OQUFRT/bundle.json","state":"https://pith.science/pith/IXX6HMK55IVNKWI3HJL6OQUFRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXX6HMK55IVNKWI3HJL6OQUFRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IXX6HMK55IVNKWI3HJL6OQUFRT","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":"f942798d38e121512ae34c76a87d72e8644ca5502ff966d54639127664b20fc7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:59:56Z","title_canon_sha256":"6182e7cd3bf959f244fd773d5f24d20464aa260b185ed4d690e57ad3b628a19e"},"schema_version":"1.0","source":{"id":"2607.28627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28627","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28627v1","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28627","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"IXX6HMK55IVN","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"pith_short_16","alias_value":"IXX6HMK55IVNKWI3","created_at":"2026-07-31T01:39:09Z"},{"alias_kind":"pith_short_8","alias_value":"IXX6HMK5","created_at":"2026-07-31T01:39:09Z"}],"graph_snapshots":[{"event_id":"sha256:651f30159ebc4087b06c7315389d3ff9cf977d29a275c38836404cbe7d1445aa","target":"graph","created_at":"2026-07-31T01:39:09Z","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/2607.28627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints. We present ReToken, a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache. Trained on only a small image-QA dataset, ReToken yields consistent gains across image and video benchmarks: on Visual Haystacks it improves Qwen3VL-8B by 13.4 points and InternVL3.5 by 12.4 points (>2","authors_text":"Derek Hoiem, Jianfeng Gao, Reuben Tan, Yao Xiao, Yuqun Wu, Zhen Zhu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:59:56Z","title":"ReToken: One Token to Improve Vision-Language Models for Visual Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28627","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":"sha256:1436ab4c59e3d72c620b33b0ef00f6c02553ca45b807129ffa467135af2c4faf","target":"record","created_at":"2026-07-31T01:39:09Z","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":"f942798d38e121512ae34c76a87d72e8644ca5502ff966d54639127664b20fc7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:59:56Z","title_canon_sha256":"6182e7cd3bf959f244fd773d5f24d20464aa260b185ed4d690e57ad3b628a19e"},"schema_version":"1.0","source":{"id":"2607.28627","kind":"arxiv","version":1}},"canonical_sha256":"45efe3b15dea2ad5591b3a57e742858ce2dcd9bac6a7aa6d50ddc1c50b497a98","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45efe3b15dea2ad5591b3a57e742858ce2dcd9bac6a7aa6d50ddc1c50b497a98","first_computed_at":"2026-07-31T01:39:09.180132Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:39:09.180132Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1436ab4c59e3d72c620b33b0ef00f6c02553ca45b807129ffa467135af2c4faf","sha256:651f30159ebc4087b06c7315389d3ff9cf977d29a275c38836404cbe7d1445aa"],"state_sha256":"55b2f169e3530379f17f846ce71101489b5fd629a633b088b38256b5beb2908f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVdvB4kLk8B3Gz8uLrzd1QX0uxVJHvyU8H6sY/oetCcE09QHtfDjGzDnxXPJ6ODiQnO2jSp71+qMuOwSv1B9Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T04:40:30.808745Z","bundle_sha256":"a57d5f4669c8eae59c781d20b1bfdc06471a9b3bf58387fa1e1bb8f2b26bf7da"}}