{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XKZXOAW3WCS7RITEBLXGTGMOCD","short_pith_number":"pith:XKZXOAW3","canonical_record":{"source":{"id":"2408.11795","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"c80f4b70ffdff311b3ed80626a5e9900401db27c06deedbfdc58bd5d50ac86f1","abstract_canon_sha256":"ce55024c5b4b5353b507325ac22eb34cdf0b51e7419ff7540bb2025a952566fd"},"schema_version":"1.0"},"canonical_sha256":"bab37702dbb0a5f8a2640aee69998e10ed1ac97bacc2cfeaf469c9eb038131f4","source":{"kind":"arxiv","id":"2408.11795","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11795","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11795v3","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11795","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"XKZXOAW3WCS7","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"XKZXOAW3WCS7RITE","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"XKZXOAW3","created_at":"2026-07-05T10:45:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XKZXOAW3WCS7RITEBLXGTGMOCD","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11795","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"c80f4b70ffdff311b3ed80626a5e9900401db27c06deedbfdc58bd5d50ac86f1","abstract_canon_sha256":"ce55024c5b4b5353b507325ac22eb34cdf0b51e7419ff7540bb2025a952566fd"},"schema_version":"1.0"},"canonical_sha256":"bab37702dbb0a5f8a2640aee69998e10ed1ac97bacc2cfeaf469c9eb038131f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:11.002293Z","signature_b64":"0JtmSGx3cAvtlfFnS6yyScv+hunzgLkM9DMRtveS5HG8tT4MhUXOqTHjLXHAB45GCbSVg67xgOfSOWHEGvX7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bab37702dbb0a5f8a2640aee69998e10ed1ac97bacc2cfeaf469c9eb038131f4","last_reissued_at":"2026-07-05T10:45:11.001829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:11.001829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11795","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IqEA/2ic6iNkQ5vLVXDPUsPqDku9NEj3c42IWz4JAsoJzeyMl302THDXOXddv+cJpqzJJwW4eM8JRuTKp4kKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:55:29.881440Z"},"content_sha256":"aee99cbc54f2b44fa25d58d7d1c78852e975acf8a20749d40a57043a2a9d2aa0","schema_version":"1.0","event_id":"sha256:aee99cbc54f2b44fa25d58d7d1c78852e975acf8a20749d40a57043a2a9d2aa0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XKZXOAW3WCS7RITEBLXGTGMOCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feipeng Ma, Fengyun Rao, Hebei Li, Shilin Yan, Siying Wu, Xiaoyan Sun, Yizhou Zhou, Yueyi Zhang, Zheyu Zhang, Zilong He","submitted_at":"2024-08-21T17:36:37Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated satisfactory performance across various vision-language tasks. Current approaches for vision and language interaction fall into two categories: self-attention-based and cross-attention-based methods. However, both approaches present inherent limitations, forcing a trade-off between data and computational efficiency. To address this issue, we introduce the Data-$\\textbf{E}$fficient and Compute-$\\textbf{E}$fficient $\\textbf{MLLM}$ ($\\textbf{EE-MLLM}$). Specifically, we modify the original self-attention mechanism i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11795","kind":"arxiv","version":3},"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/2408.11795/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":"2026-07-05T10:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pa+Z1Z2OOhuHXgm1+jaMjAFTERnwrUGo2mo+ewucywB9h+ivUas/K5JZksewm1HeH8ViH+64DWk1jipJSVofBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:55:29.882024Z"},"content_sha256":"3ea66631ce78b6eb23023cd2bc5a70cf2cd0f6c41f8936bd296a5b1a418a4ecd","schema_version":"1.0","event_id":"sha256:3ea66631ce78b6eb23023cd2bc5a70cf2cd0f6c41f8936bd296a5b1a418a4ecd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKZXOAW3WCS7RITEBLXGTGMOCD/bundle.json","state_url":"https://pith.science/pith/XKZXOAW3WCS7RITEBLXGTGMOCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKZXOAW3WCS7RITEBLXGTGMOCD/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":"2026-08-08T17:55:29Z","links":{"resolver":"https://pith.science/pith/XKZXOAW3WCS7RITEBLXGTGMOCD","bundle":"https://pith.science/pith/XKZXOAW3WCS7RITEBLXGTGMOCD/bundle.json","state":"https://pith.science/pith/XKZXOAW3WCS7RITEBLXGTGMOCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKZXOAW3WCS7RITEBLXGTGMOCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XKZXOAW3WCS7RITEBLXGTGMOCD","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":"ce55024c5b4b5353b507325ac22eb34cdf0b51e7419ff7540bb2025a952566fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:36:37Z","title_canon_sha256":"c80f4b70ffdff311b3ed80626a5e9900401db27c06deedbfdc58bd5d50ac86f1"},"schema_version":"1.0","source":{"id":"2408.11795","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11795","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11795v3","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11795","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"XKZXOAW3WCS7","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"XKZXOAW3WCS7RITE","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"XKZXOAW3","created_at":"2026-07-05T10:45:11Z"}],"graph_snapshots":[{"event_id":"sha256:3ea66631ce78b6eb23023cd2bc5a70cf2cd0f6c41f8936bd296a5b1a418a4ecd","target":"graph","created_at":"2026-07-05T10:45:11Z","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/2408.11795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated satisfactory performance across various vision-language tasks. Current approaches for vision and language interaction fall into two categories: self-attention-based and cross-attention-based methods. However, both approaches present inherent limitations, forcing a trade-off between data and computational efficiency. To address this issue, we introduce the Data-$\\textbf{E}$fficient and Compute-$\\textbf{E}$fficient $\\textbf{MLLM}$ ($\\textbf{EE-MLLM}$). Specifically, we modify the original self-attention mechanism i","authors_text":"Feipeng Ma, Fengyun Rao, Hebei Li, Shilin Yan, Siying Wu, Xiaoyan Sun, Yizhou Zhou, Yueyi Zhang, Zheyu Zhang, Zilong He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:36:37Z","title":"EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11795","kind":"arxiv","version":3},"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:aee99cbc54f2b44fa25d58d7d1c78852e975acf8a20749d40a57043a2a9d2aa0","target":"record","created_at":"2026-07-05T10:45:11Z","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":"ce55024c5b4b5353b507325ac22eb34cdf0b51e7419ff7540bb2025a952566fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:36:37Z","title_canon_sha256":"c80f4b70ffdff311b3ed80626a5e9900401db27c06deedbfdc58bd5d50ac86f1"},"schema_version":"1.0","source":{"id":"2408.11795","kind":"arxiv","version":3}},"canonical_sha256":"bab37702dbb0a5f8a2640aee69998e10ed1ac97bacc2cfeaf469c9eb038131f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bab37702dbb0a5f8a2640aee69998e10ed1ac97bacc2cfeaf469c9eb038131f4","first_computed_at":"2026-07-05T10:45:11.001829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:11.001829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JtmSGx3cAvtlfFnS6yyScv+hunzgLkM9DMRtveS5HG8tT4MhUXOqTHjLXHAB45GCbSVg67xgOfSOWHEGvX7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:11.002293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11795","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aee99cbc54f2b44fa25d58d7d1c78852e975acf8a20749d40a57043a2a9d2aa0","sha256:3ea66631ce78b6eb23023cd2bc5a70cf2cd0f6c41f8936bd296a5b1a418a4ecd"],"state_sha256":"fee996adff73617b3c974c5ac1d98eaf56d935d8e4d55e3af269f6eb7cab2927"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RVmlok4PQVy+zs2AAtvGMsCcHNCTF2PDrpY2f5JELKGfqxGy3DkxKNjHxbdxNBhhUSyGV5AlN9rmP3hbJq/MDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:55:29.885933Z","bundle_sha256":"3e19fb6bad51fc4856087675e1e44a6452655ab37a842dbb2556735e5dd36fc2"}}