{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YIZFMA3WHXN33AD6B2YIMADYKP","short_pith_number":"pith:YIZFMA3W","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"},"canonical_sha256":"c2325603763ddbbd807e0eb086007853c7396175d5794acff915e565a27f22e4","source":{"kind":"arxiv","id":"2608.08630","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YIZFMA3WHXN33AD6B2YIMADYKP","target":"record","payload":{"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"},"canonical_sha256":"c2325603763ddbbd807e0eb086007853c7396175d5794acff915e565a27f22e4","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"},"source_kind":"arxiv","source_id":"2608.08630","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":"2026-08-11T01:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XIiHmIxooSQfVIBQLKeMwOmc80YaMMlq+bRxHy6JIpbccO45yGPvW4CfUtqbE0Z5nIPqvGMm5dcsdaFy1DP7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:53:21.457067Z"},"content_sha256":"b8fe6757d9de3abeb23af8bdc06657da59adefe3c810fd3ba21109bc8b593268","schema_version":"1.0","event_id":"sha256:b8fe6757d9de3abeb23af8bdc06657da59adefe3c810fd3ba21109bc8b593268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YIZFMA3WHXN33AD6B2YIMADYKP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-11T01:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VSgEpG8W4xsREvWC5ze4Y7tcW8tE/kLFpdWU6E40cVEZ8oibxob1ZjCRzmkZqA3Uq7Py1Oacw1mvR7S6xE/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:53:21.457416Z"},"content_sha256":"e27d8e0f0591cda7eaa6502724a63b80705f0497fa39e22d0ef25059529bcc4d","schema_version":"1.0","event_id":"sha256:e27d8e0f0591cda7eaa6502724a63b80705f0497fa39e22d0ef25059529bcc4d"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YIZFMA3WHXN33AD6B2YIMADYKP","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/V1/2023.EMNLP-MAIN.20) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.: Evaluating object hallu- cination in large vision-language models. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Langua","arxiv_id":"2608.08630","detector":"doi_compliance","evidence":{"ref_index":15,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2023","reconstructed_doi":"10.18653/V1/2023.EMNLP-MAIN.20"},"severity":"advisory","ref_index":15,"audited_at":"2026-08-14T05:09:04.400185Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/V1/2023.EMNLP-MAIN.20","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"7858af0ee4804691746bba3ee13335e1f551f8e386956f8e2c0008371f15bae3","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19601,"payload_sha256":"c7a86d3156a5edd1acb80a7019e78f3a01808449b15ad9b2f3ccde23cbe064a5","signature_b64":"SmxNZqaY70Iv1tjbsNnAI6SuWUeah7CEaEBHA8rI+U2I/E2sgRezOMe3bJfbyFcd0cujrOfFuTVFN0v53kkaAw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T05:13:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ogg+Lfuq7CFErppwG5aUUjAkD3lF5iib42wbE+lK2ONAHICA/tq54c6dWzREQMA/cszBeR1P7LnuouwDbg/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:53:21.464057Z"},"content_sha256":"16b52de638595b91d95be0362d8243ecad67e04eeb36975dd0c7cb887d966686","schema_version":"1.0","event_id":"sha256:16b52de638595b91d95be0362d8243ecad67e04eeb36975dd0c7cb887d966686"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/bundle.json","state_url":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIZFMA3WHXN33AD6B2YIMADYKP/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":"2026-08-18T21:53:21Z","links":{"resolver":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP","bundle":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/bundle.json","state":"https://pith.science/pith/YIZFMA3WHXN33AD6B2YIMADYKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIZFMA3WHXN33AD6B2YIMADYKP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRJMmuW+GSB3zNaiePgggSFS3scPjqpZuwh3I+Puugr09Tdux9fsDe9me4hO3MnxZ5bIDX8RgxDkhlBTj7DeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:53:21.465510Z","bundle_sha256":"c9cdbaab528c64fdf9cd2315af3e66cfa41f749afa25b1dde8e595e6e89ad08a"}}