{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5P7OQNCQ4SNTUAVXMSVYHQ3ZNN","short_pith_number":"pith:5P7OQNCQ","canonical_record":{"source":{"id":"2407.19651","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T02:32:44Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"678206982fb45bef21c48d2eb98d4eef5de9e6fc713da47eb464bc2a8bb419a3","abstract_canon_sha256":"c44c57f05538a6fcc67f28d76d8c62315476291e03abe0003fd4ffdd64d5ca39"},"schema_version":"1.0"},"canonical_sha256":"ebfee83450e49b3a02b764ab83c3796b602071a076f274aa964768ff8ef3ea57","source":{"kind":"arxiv","id":"2407.19651","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19651","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19651v2","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19651","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"5P7OQNCQ4SNT","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"5P7OQNCQ4SNTUAVX","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"5P7OQNCQ","created_at":"2026-07-05T10:15:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5P7OQNCQ4SNTUAVXMSVYHQ3ZNN","target":"record","payload":{"canonical_record":{"source":{"id":"2407.19651","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T02:32:44Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"678206982fb45bef21c48d2eb98d4eef5de9e6fc713da47eb464bc2a8bb419a3","abstract_canon_sha256":"c44c57f05538a6fcc67f28d76d8c62315476291e03abe0003fd4ffdd64d5ca39"},"schema_version":"1.0"},"canonical_sha256":"ebfee83450e49b3a02b764ab83c3796b602071a076f274aa964768ff8ef3ea57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:18.553463Z","signature_b64":"BmgJXw6Lq4k6oErel5KroCyAYah3iAzJg0P9RNyvdiOIvjgi8PtUYHbX02JjR+EPUzGFWB2YZiu+vACVOPD4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebfee83450e49b3a02b764ab83c3796b602071a076f274aa964768ff8ef3ea57","last_reissued_at":"2026-07-05T10:15:18.552971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:18.552971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.19651","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":"2026-07-05T10:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YEp99PoHbY1nBiRxWWQtmpI1obbYNYz8vO8TDHPBMj7sU7YRHXgdjkn8t3a/y5Bq9sWAzF90q98rMKjwj3GkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:03:40.820755Z"},"content_sha256":"f2f7929d64772add3fda5e19a262d1290b7a74f22d7f0f5a6d30193aa7b1c625","schema_version":"1.0","event_id":"sha256:f2f7929d64772add3fda5e19a262d1290b7a74f22d7f0f5a6d30193aa7b1c625"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5P7OQNCQ4SNTUAVXMSVYHQ3ZNN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Compressed Image Latents and Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Alessandro Gnutti, Cheng Chien, Chia-Hao Kao, Riccardo Leonardi, Shao-Yuan Lo, Wen-Hsiao Peng, Yi-Hsin Chen, Yu-Jen Tseng","submitted_at":"2024-07-29T02:32:44Z","abstract_excerpt":"This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs). MLLMs have extended the success of large language models to modalities (e.g. images) beyond text, but their billion scale hinders deployment on resource-constrained end devices. While cloud-hosted MLLMs could be available, transmitting raw, uncompressed images captured by end devices to the cloud requires an efficient image compression system. To address this, we focus on emerging neural image compression and propose a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19651","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/2407.19651/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":"2026-07-05T10:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmF5kh4/pHWFkMPd77zHjP2Gky1QpknxBFu8YMVpT6A22ZpL6g2nPHZEFbMrarDcqj+31Bsmyxh6CWOiOzMlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:03:40.821316Z"},"content_sha256":"40c33e91637b1b4f00a541cb9ff3a428560950b5b0684dc83cc6015059bd4694","schema_version":"1.0","event_id":"sha256:40c33e91637b1b4f00a541cb9ff3a428560950b5b0684dc83cc6015059bd4694"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5P7OQNCQ4SNTUAVXMSVYHQ3ZNN/bundle.json","state_url":"https://pith.science/pith/5P7OQNCQ4SNTUAVXMSVYHQ3ZNN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5P7OQNCQ4SNTUAVXMSVYHQ3ZNN/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":"2026-08-17T14:03:40Z","links":{"resolver":"https://pith.science/pith/5P7OQNCQ4SNTUAVXMSVYHQ3ZNN","bundle":"https://pith.science/pith/5P7OQNCQ4SNTUAVXMSVYHQ3ZNN/bundle.json","state":"https://pith.science/pith/5P7OQNCQ4SNTUAVXMSVYHQ3ZNN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5P7OQNCQ4SNTUAVXMSVYHQ3ZNN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5P7OQNCQ4SNTUAVXMSVYHQ3ZNN","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":"c44c57f05538a6fcc67f28d76d8c62315476291e03abe0003fd4ffdd64d5ca39","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T02:32:44Z","title_canon_sha256":"678206982fb45bef21c48d2eb98d4eef5de9e6fc713da47eb464bc2a8bb419a3"},"schema_version":"1.0","source":{"id":"2407.19651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19651","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19651v2","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19651","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"5P7OQNCQ4SNT","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"5P7OQNCQ4SNTUAVX","created_at":"2026-07-05T10:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"5P7OQNCQ","created_at":"2026-07-05T10:15:18Z"}],"graph_snapshots":[{"event_id":"sha256:40c33e91637b1b4f00a541cb9ff3a428560950b5b0684dc83cc6015059bd4694","target":"graph","created_at":"2026-07-05T10:15:18Z","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/2407.19651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs). MLLMs have extended the success of large language models to modalities (e.g. images) beyond text, but their billion scale hinders deployment on resource-constrained end devices. While cloud-hosted MLLMs could be available, transmitting raw, uncompressed images captured by end devices to the cloud requires an efficient image compression system. To address this, we focus on emerging neural image compression and propose a n","authors_text":"Alessandro Gnutti, Cheng Chien, Chia-Hao Kao, Riccardo Leonardi, Shao-Yuan Lo, Wen-Hsiao Peng, Yi-Hsin Chen, Yu-Jen Tseng","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T02:32:44Z","title":"Bridging Compressed Image Latents and Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19651","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:f2f7929d64772add3fda5e19a262d1290b7a74f22d7f0f5a6d30193aa7b1c625","target":"record","created_at":"2026-07-05T10:15:18Z","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":"c44c57f05538a6fcc67f28d76d8c62315476291e03abe0003fd4ffdd64d5ca39","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T02:32:44Z","title_canon_sha256":"678206982fb45bef21c48d2eb98d4eef5de9e6fc713da47eb464bc2a8bb419a3"},"schema_version":"1.0","source":{"id":"2407.19651","kind":"arxiv","version":2}},"canonical_sha256":"ebfee83450e49b3a02b764ab83c3796b602071a076f274aa964768ff8ef3ea57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebfee83450e49b3a02b764ab83c3796b602071a076f274aa964768ff8ef3ea57","first_computed_at":"2026-07-05T10:15:18.552971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:18.552971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BmgJXw6Lq4k6oErel5KroCyAYah3iAzJg0P9RNyvdiOIvjgi8PtUYHbX02JjR+EPUzGFWB2YZiu+vACVOPD4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:18.553463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.19651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2f7929d64772add3fda5e19a262d1290b7a74f22d7f0f5a6d30193aa7b1c625","sha256:40c33e91637b1b4f00a541cb9ff3a428560950b5b0684dc83cc6015059bd4694"],"state_sha256":"63361607b0987ab443edf0e3848e3bf3c435da555375b3658d11f4e47d2d36ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Jdjer9zCkM6DO96Ul4f+Z5XfEkmz1RQjxKOXLnWhn2BqS7VFwC8P+DHvFq6u5rZOgutMcekP2Gq/QJ5/QSQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:03:40.825075Z","bundle_sha256":"f2c1ec14bffe96f4a3252a9e7efe1fbc3f5dabe051cd85d6c1868fa48da669e0"}}