{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YIZFMA3WHXN33AD6B2YIMADYKP","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b15b770b77e61a50f97a9cf277eff21c9188922e99b05ea843ab7cd03d180591","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T10:31:03Z","title_canon_sha256":"4c324f6521157cbdc02e888bee7cafedec7c2f843a6c82e662e7adff262455d1"},"schema_version":"1.0","source":{"id":"2608.08630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08630","created_at":"2026-08-11T01:23:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08630v1","created_at":"2026-08-11T01:23:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08630","created_at":"2026-08-11T01:23:13Z"},{"alias_kind":"pith_short_12","alias_value":"YIZFMA3WHXN3","created_at":"2026-08-11T01:23:13Z"},{"alias_kind":"pith_short_16","alias_value":"YIZFMA3WHXN33AD6","created_at":"2026-08-11T01:23:13Z"},{"alias_kind":"pith_short_8","alias_value":"YIZFMA3W","created_at":"2026-08-11T01:23:13Z"}],"graph_snapshots":[{"event_id":"sha256:e27d8e0f0591cda7eaa6502724a63b80705f0497fa39e22d0ef25059529bcc4d","target":"graph","created_at":"2026-08-11T01:23:13Z","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/2608.08630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-attention. Current solutions either resort to aggressive token pruning, risking irreversible information loss, or adopt efficient but less precise architectures, while largely ignoring the equally vital textual component. We introduce VLZip, a framework that unifies visual and textual compression for high-fidelity reasoning within a pure Transformer. At its core, VLZip hierarchically distills visual and textual segments into compact, layer-specific","authors_text":"Cheng Chen, Hang Yu, Lingchen Meng, Peng Di, Wenjie Yang, Yu-Gang Jiang, Yuqi Zhang, Yuyu Guo, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T10:31:03Z","title":"VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08630","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:b8fe6757d9de3abeb23af8bdc06657da59adefe3c810fd3ba21109bc8b593268","target":"record","created_at":"2026-08-11T01:23:13Z","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":"b15b770b77e61a50f97a9cf277eff21c9188922e99b05ea843ab7cd03d180591","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T10:31:03Z","title_canon_sha256":"4c324f6521157cbdc02e888bee7cafedec7c2f843a6c82e662e7adff262455d1"},"schema_version":"1.0","source":{"id":"2608.08630","kind":"arxiv","version":1}},"canonical_sha256":"c2325603763ddbbd807e0eb086007853c7396175d5794acff915e565a27f22e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2325603763ddbbd807e0eb086007853c7396175d5794acff915e565a27f22e4","first_computed_at":"2026-08-11T01:23:13.323351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:23:13.323351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zglSk48oqIt7KG0nqI9qMwSpFYhZVu4vRsvsZURXAD4h0KtWGoSCFHRstLZidV3vO6uxadSvyIRmu52DZvJRDQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:23:13.325773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8fe6757d9de3abeb23af8bdc06657da59adefe3c810fd3ba21109bc8b593268","sha256:e27d8e0f0591cda7eaa6502724a63b80705f0497fa39e22d0ef25059529bcc4d","sha256:16b52de638595b91d95be0362d8243ecad67e04eeb36975dd0c7cb887d966686"],"state_sha256":"f00f755c6fa5ee6da0e7a8038b7ba424646fa635806461953a8e89f6b6c31877"}