{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HU44CG3YHBSQPWFTHLYQ25HYCN","short_pith_number":"pith:HU44CG3Y","canonical_record":{"source":{"id":"2606.04433","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T04:31:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7ffac6c6592845b0ff567f6f5299c116180b678e38a74ffafc6a247bdc36c8e6","abstract_canon_sha256":"f143705a769c16d84e5d8a5573357e8e0420a8ef7c27ee826b37867b499817be"},"schema_version":"1.0"},"canonical_sha256":"3d39c11b78386507d8b33af10d74f81368f246463cdf8c78f8dae4b08f287bd8","source":{"kind":"arxiv","id":"2606.04433","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04433","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04433v1","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04433","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"HU44CG3YHBSQ","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"HU44CG3YHBSQPWFT","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"HU44CG3Y","created_at":"2026-06-04T01:09:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HU44CG3YHBSQPWFTHLYQ25HYCN","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04433","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T04:31:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7ffac6c6592845b0ff567f6f5299c116180b678e38a74ffafc6a247bdc36c8e6","abstract_canon_sha256":"f143705a769c16d84e5d8a5573357e8e0420a8ef7c27ee826b37867b499817be"},"schema_version":"1.0"},"canonical_sha256":"3d39c11b78386507d8b33af10d74f81368f246463cdf8c78f8dae4b08f287bd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:07.957481Z","signature_b64":"lybAbNsA9ewOH0wecBoI8FNXKMb/f0E0lAwaNfkElyw8iaVJe+57fydGLGqrnKi36aUqx3fyAOArinfynNl7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d39c11b78386507d8b33af10d74f81368f246463cdf8c78f8dae4b08f287bd8","last_reissued_at":"2026-06-04T01:09:07.957057Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:07.957057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04433","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":"2026-06-04T01:09:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qxVcjn0iliLxseJXHTXEAOUyVZ2FrWZSPHBLbrV62FZsDBPGi3lG76ceLUU+yR2iDDN9QmG/yJTMMhGrv4NBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T01:42:04.639790Z"},"content_sha256":"d099c38a5c7e4dbcaa5ea52bf2f1581e81027e5659d2bf7701b1ecab79bbab86","schema_version":"1.0","event_id":"sha256:d099c38a5c7e4dbcaa5ea52bf2f1581e81027e5659d2bf7701b1ecab79bbab86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HU44CG3YHBSQPWFTHLYQ25HYCN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stateful Visual Encoders for Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adam Yala, David M. Chan, Joseph E. Gonzalez, Junwei Yu, Trevor Darrell, Zirui Wang","submitted_at":"2026-06-03T04:31:15Z","abstract_excerpt":"Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, visual comparisons happen only inside the language model, while the visual encoder itself remains stateless: each image is encoded independently, without access to the prior visual context. As a result, small but task-critical changes may be attenuated before the language model has a chance to compare them, especially when those changes do not affect the high-level semantics of the scene. We introduce a Stateful Visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04433","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/2606.04433/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":"2026-06-04T01:09:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h9GNJEjNbNK3WnOuYD5+bIHuHlAzK9jXEeAqrOlFNGWG9azUSixT/ZmXgzGzfnvUnKmJbspofX1NAjIhuKKzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T01:42:04.640158Z"},"content_sha256":"a7983e17f6c7883ae174c4d76e62538244c8bea08ac6c61bba9b426eceb5c212","schema_version":"1.0","event_id":"sha256:a7983e17f6c7883ae174c4d76e62538244c8bea08ac6c61bba9b426eceb5c212"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HU44CG3YHBSQPWFTHLYQ25HYCN/bundle.json","state_url":"https://pith.science/pith/HU44CG3YHBSQPWFTHLYQ25HYCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HU44CG3YHBSQPWFTHLYQ25HYCN/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":"2026-06-29T01:42:04Z","links":{"resolver":"https://pith.science/pith/HU44CG3YHBSQPWFTHLYQ25HYCN","bundle":"https://pith.science/pith/HU44CG3YHBSQPWFTHLYQ25HYCN/bundle.json","state":"https://pith.science/pith/HU44CG3YHBSQPWFTHLYQ25HYCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HU44CG3YHBSQPWFTHLYQ25HYCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HU44CG3YHBSQPWFTHLYQ25HYCN","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":"f143705a769c16d84e5d8a5573357e8e0420a8ef7c27ee826b37867b499817be","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T04:31:15Z","title_canon_sha256":"7ffac6c6592845b0ff567f6f5299c116180b678e38a74ffafc6a247bdc36c8e6"},"schema_version":"1.0","source":{"id":"2606.04433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04433","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04433v1","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04433","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"HU44CG3YHBSQ","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"HU44CG3YHBSQPWFT","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"HU44CG3Y","created_at":"2026-06-04T01:09:07Z"}],"graph_snapshots":[{"event_id":"sha256:a7983e17f6c7883ae174c4d76e62538244c8bea08ac6c61bba9b426eceb5c212","target":"graph","created_at":"2026-06-04T01:09:07Z","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/2606.04433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, visual comparisons happen only inside the language model, while the visual encoder itself remains stateless: each image is encoded independently, without access to the prior visual context. As a result, small but task-critical changes may be attenuated before the language model has a chance to compare them, especially when those changes do not affect the high-level semantics of the scene. We introduce a Stateful Visual ","authors_text":"Adam Yala, David M. Chan, Joseph E. Gonzalez, Junwei Yu, Trevor Darrell, Zirui Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T04:31:15Z","title":"Stateful Visual Encoders for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04433","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:d099c38a5c7e4dbcaa5ea52bf2f1581e81027e5659d2bf7701b1ecab79bbab86","target":"record","created_at":"2026-06-04T01:09:07Z","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":"f143705a769c16d84e5d8a5573357e8e0420a8ef7c27ee826b37867b499817be","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T04:31:15Z","title_canon_sha256":"7ffac6c6592845b0ff567f6f5299c116180b678e38a74ffafc6a247bdc36c8e6"},"schema_version":"1.0","source":{"id":"2606.04433","kind":"arxiv","version":1}},"canonical_sha256":"3d39c11b78386507d8b33af10d74f81368f246463cdf8c78f8dae4b08f287bd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d39c11b78386507d8b33af10d74f81368f246463cdf8c78f8dae4b08f287bd8","first_computed_at":"2026-06-04T01:09:07.957057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:07.957057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lybAbNsA9ewOH0wecBoI8FNXKMb/f0E0lAwaNfkElyw8iaVJe+57fydGLGqrnKi36aUqx3fyAOArinfynNl7Bg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:07.957481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d099c38a5c7e4dbcaa5ea52bf2f1581e81027e5659d2bf7701b1ecab79bbab86","sha256:a7983e17f6c7883ae174c4d76e62538244c8bea08ac6c61bba9b426eceb5c212"],"state_sha256":"bacccdf9ca8d31fae010d2d18f8875abd0c89e87d239eba28091df594fb1813e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95Q50y7n7aOJofOMd6xQQw+ghTzYn/bjDXXBqE7d5npKfKeyDE0temIkppxocZ90TIvqGJbeJS5Y4mQspJjSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T01:42:04.642087Z","bundle_sha256":"c61fe2af633803c959e28af0258dbdbac4fb88f6a29cdee2d843a3476b30712d"}}