{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YIZFMA3WHXN33AD6B2YIMADYKP","short_pith_number":"pith:YIZFMA3W","schema_version":"1.0","canonical_sha256":"c2325603763ddbbd807e0eb086007853c7396175d5794acff915e565a27f22e4","source":{"kind":"arxiv","id":"2608.08630","version":1},"attestation_state":"computed","paper":{"title":"VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Chen, Hang Yu, Lingchen Meng, Peng Di, Wenjie Yang, Yu-Gang Jiang, Yuqi Zhang, Yuyu Guo, Zuxuan Wu","submitted_at":"2026-08-09T10:31:03Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.08630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T10:31:03Z","cross_cats_sorted":[],"title_canon_sha256":"4c324f6521157cbdc02e888bee7cafedec7c2f843a6c82e662e7adff262455d1","abstract_canon_sha256":"b15b770b77e61a50f97a9cf277eff21c9188922e99b05ea843ab7cd03d180591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:13.325773Z","signature_b64":"zglSk48oqIt7KG0nqI9qMwSpFYhZVu4vRsvsZURXAD4h0KtWGoSCFHRstLZidV3vO6uxadSvyIRmu52DZvJRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2325603763ddbbd807e0eb086007853c7396175d5794acff915e565a27f22e4","last_reissued_at":"2026-08-11T01:23:13.323351Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:13.323351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Chen, Hang Yu, Lingchen Meng, Peng Di, Wenjie Yang, Yu-Gang Jiang, Yuqi Zhang, Yuyu Guo, Zuxuan Wu","submitted_at":"2026-08-09T10:31:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08630","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/2608.08630/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.08630","created_at":"2026-08-11T01:23:13.324161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08630v1","created_at":"2026-08-11T01:23:13.324161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08630","created_at":"2026-08-11T01:23:13.324161+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIZFMA3WHXN3","created_at":"2026-08-11T01:23:13.324161+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIZFMA3WHXN33AD6","created_at":"2026-08-11T01:23:13.324161+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIZFMA3W","created_at":"2026-08-11T01:23:13.324161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP","json":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP.json","graph_json":"https://pith.science/api/pith-number/YIZFMA3WHXN33AD6B2YIMADYKP/graph.json","events_json":"https://pith.science/api/pith-number/YIZFMA3WHXN33AD6B2YIMADYKP/events.json","paper":"https://pith.science/paper/YIZFMA3W"},"agent_actions":{"view_html":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP","download_json":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP.json","view_paper":"https://pith.science/paper/YIZFMA3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08630&json=true","fetch_graph":"https://pith.science/api/pith-number/YIZFMA3WHXN33AD6B2YIMADYKP/graph.json","fetch_events":"https://pith.science/api/pith-number/YIZFMA3WHXN33AD6B2YIMADYKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/action/storage_attestation","attest_author":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/action/author_attestation","sign_citation":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/action/citation_signature","submit_replication":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/action/replication_record"}},"created_at":"2026-08-11T01:23:13.324161+00:00","updated_at":"2026-08-11T01:23:13.324161+00:00"}