{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3ZI6UG36AFGWVOFYSBJJGPMMGK","short_pith_number":"pith:3ZI6UG36","canonical_record":{"source":{"id":"2406.12275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T05:05:12Z","cross_cats_sorted":[],"title_canon_sha256":"ad893f2b7f2d285d2569d4147c47250ce3cdf5d5f7a193cecefb1818e716647a","abstract_canon_sha256":"b425fb548f2ac6988656baaa95911c41b417eb9680741739c27ff6ba0c9fc003"},"schema_version":"1.0"},"canonical_sha256":"de51ea1b7e014d6ab8b89052933d8c329dbf257ce7a7467ce8385fd828cb1055","source":{"kind":"arxiv","id":"2406.12275","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12275","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12275v2","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12275","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"3ZI6UG36AFGW","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"3ZI6UG36AFGWVOFY","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"3ZI6UG36","created_at":"2026-07-05T10:22:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3ZI6UG36AFGWVOFYSBJJGPMMGK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T05:05:12Z","cross_cats_sorted":[],"title_canon_sha256":"ad893f2b7f2d285d2569d4147c47250ce3cdf5d5f7a193cecefb1818e716647a","abstract_canon_sha256":"b425fb548f2ac6988656baaa95911c41b417eb9680741739c27ff6ba0c9fc003"},"schema_version":"1.0"},"canonical_sha256":"de51ea1b7e014d6ab8b89052933d8c329dbf257ce7a7467ce8385fd828cb1055","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:47.255960Z","signature_b64":"q98qxi6hw2jZBThKP61NAO9liwcaiWPjSc6YMEPwFeq1nngLXbsAm5VKpaCFEMnuFmFDcBhzS1c2BKIX0ApwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de51ea1b7e014d6ab8b89052933d8c329dbf257ce7a7467ce8385fd828cb1055","last_reissued_at":"2026-07-05T10:22:47.255345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:47.255345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12275","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UuETXqhEwLzCJ6J9MiKN2h9uVTvvxf7iGnUTVJzr+ogSEGBwpLoDDf35j6ACTa/bPNOXTxa39CsY7ANB4KB+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:12:20.483814Z"},"content_sha256":"087da900e0b0f4ef4559b02de8f23e8427e87b31beb6f07cca1c8dbc2803d62f","schema_version":"1.0","event_id":"sha256:087da900e0b0f4ef4559b02de8f23e8427e87b31beb6f07cca1c8dbc2803d62f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3ZI6UG36AFGWVOFYSBJJGPMMGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaoke Huang, Xubing Ye, Yansong Tang, Yixiao Ge, Yukang Gan","submitted_at":"2024-06-18T05:05:12Z","abstract_excerpt":"Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window and high computational cost of processing high-resolution image inputs and videos. Vision compression can alleviate this problem by reducing the vision token count. Previous approaches compress vision tokens with external modules and force LLMs to understand the compressed ones, leading to visual information loss. However, the LLMs' understanding paradigm of vision tokens is not fully utilised in the compression learning process. We propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12275","kind":"arxiv","version":2},"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/2406.12275/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":"2026-07-05T10:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXkhaLcjEIK1xk4lrV0WwzoV59i/hdwHm2E4VvcnX3Ta2nWi2EIJIwhneeiXMKJmRRN32Eipq2DikGVXWqvUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:12:20.484192Z"},"content_sha256":"341f0943715d9deabdf21af3eff606ec3a7e3407bd4f4da62faa13cedb4eac7c","schema_version":"1.0","event_id":"sha256:341f0943715d9deabdf21af3eff606ec3a7e3407bd4f4da62faa13cedb4eac7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZI6UG36AFGWVOFYSBJJGPMMGK/bundle.json","state_url":"https://pith.science/pith/3ZI6UG36AFGWVOFYSBJJGPMMGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZI6UG36AFGWVOFYSBJJGPMMGK/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":"2026-08-07T23:12:20Z","links":{"resolver":"https://pith.science/pith/3ZI6UG36AFGWVOFYSBJJGPMMGK","bundle":"https://pith.science/pith/3ZI6UG36AFGWVOFYSBJJGPMMGK/bundle.json","state":"https://pith.science/pith/3ZI6UG36AFGWVOFYSBJJGPMMGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZI6UG36AFGWVOFYSBJJGPMMGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3ZI6UG36AFGWVOFYSBJJGPMMGK","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":"b425fb548f2ac6988656baaa95911c41b417eb9680741739c27ff6ba0c9fc003","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T05:05:12Z","title_canon_sha256":"ad893f2b7f2d285d2569d4147c47250ce3cdf5d5f7a193cecefb1818e716647a"},"schema_version":"1.0","source":{"id":"2406.12275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12275","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12275v2","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12275","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"3ZI6UG36AFGW","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"3ZI6UG36AFGWVOFY","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"3ZI6UG36","created_at":"2026-07-05T10:22:47Z"}],"graph_snapshots":[{"event_id":"sha256:341f0943715d9deabdf21af3eff606ec3a7e3407bd4f4da62faa13cedb4eac7c","target":"graph","created_at":"2026-07-05T10:22:47Z","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/2406.12275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window and high computational cost of processing high-resolution image inputs and videos. Vision compression can alleviate this problem by reducing the vision token count. Previous approaches compress vision tokens with external modules and force LLMs to understand the compressed ones, leading to visual information loss. However, the LLMs' understanding paradigm of vision tokens is not fully utilised in the compression learning process. We propose ","authors_text":"Xiaoke Huang, Xubing Ye, Yansong Tang, Yixiao Ge, Yukang Gan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T05:05:12Z","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12275","kind":"arxiv","version":2},"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":"sha256:087da900e0b0f4ef4559b02de8f23e8427e87b31beb6f07cca1c8dbc2803d62f","target":"record","created_at":"2026-07-05T10:22:47Z","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":"b425fb548f2ac6988656baaa95911c41b417eb9680741739c27ff6ba0c9fc003","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T05:05:12Z","title_canon_sha256":"ad893f2b7f2d285d2569d4147c47250ce3cdf5d5f7a193cecefb1818e716647a"},"schema_version":"1.0","source":{"id":"2406.12275","kind":"arxiv","version":2}},"canonical_sha256":"de51ea1b7e014d6ab8b89052933d8c329dbf257ce7a7467ce8385fd828cb1055","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de51ea1b7e014d6ab8b89052933d8c329dbf257ce7a7467ce8385fd828cb1055","first_computed_at":"2026-07-05T10:22:47.255345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:47.255345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q98qxi6hw2jZBThKP61NAO9liwcaiWPjSc6YMEPwFeq1nngLXbsAm5VKpaCFEMnuFmFDcBhzS1c2BKIX0ApwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:47.255960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:087da900e0b0f4ef4559b02de8f23e8427e87b31beb6f07cca1c8dbc2803d62f","sha256:341f0943715d9deabdf21af3eff606ec3a7e3407bd4f4da62faa13cedb4eac7c"],"state_sha256":"37689c2007123d8eec5745fb1446ef2a9970573a4550f6b6173549c04334cfa5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ab7dShKwOIlqEGZi5PxhOPw7sMiKsUNf1L22hWijXM4DaXK/SjUExG74Ix4niPYf0IINvphAwt0Sr4ngyqLTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:12:20.487302Z","bundle_sha256":"37104cd0c6ffb6a3cce467a31ae6d6695f955e34bd32954cdda2937674e29be2"}}