{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4RYX6ACMVGDFJUWBNGOI7CDC7E","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":"d696a216515805a0b5ae8de82faeb677b3d68183ccede8e43919396326f7b706","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T15:24:16Z","title_canon_sha256":"afa6cdc43485e6aaebb2ca5c6da194aff679b8486c59ff9adb301b7615ec5f9f"},"schema_version":"1.0","source":{"id":"2502.02406","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02406","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02406v3","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02406","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"4RYX6ACMVGDF","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"4RYX6ACMVGDFJUWB","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"4RYX6ACM","created_at":"2026-07-05T11:10:51Z"}],"graph_snapshots":[{"event_id":"sha256:54f46433e32dbc10ef9d844c914d1d5f7ea03bf807e2ef3b407fd4b0544c12aa","target":"graph","created_at":"2026-07-05T11:10:51Z","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/2502.02406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a large number of visual tokens in cross-attention layers leads to high memory demands and often necessitates distributed computation across multiple GPUs. Existing distributed attention mechanisms face significant communication overheads, making cross-attention layers a critical bottleneck for efficient training and inference of MLLMs. To address this, we propose","authors_text":"Shivaram Venkataraman, Tzu-Tao Chang","cross_cats":["cs.AI","cs.DC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T15:24:16Z","title":"LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02406","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:c8670bdc6ac542a0e5e09192d9b53b3e061187bb252b5088424222228b1afb99","target":"record","created_at":"2026-07-05T11:10:51Z","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":"d696a216515805a0b5ae8de82faeb677b3d68183ccede8e43919396326f7b706","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T15:24:16Z","title_canon_sha256":"afa6cdc43485e6aaebb2ca5c6da194aff679b8486c59ff9adb301b7615ec5f9f"},"schema_version":"1.0","source":{"id":"2502.02406","kind":"arxiv","version":3}},"canonical_sha256":"e4717f004ca98654d2c1699c8f8862f90419b96e36a5acc34b6686c617cf29e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4717f004ca98654d2c1699c8f8862f90419b96e36a5acc34b6686c617cf29e7","first_computed_at":"2026-07-05T11:10:51.245921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:51.245921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HWTBs2D6yOfFsHnT6BG3o0HPeisVc755gMhuGboX8Tb2ffVLqOIUU19LJlLJ7S/CM4dNXjSVyfSzYUsuE4rrCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:51.246395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02406","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8670bdc6ac542a0e5e09192d9b53b3e061187bb252b5088424222228b1afb99","sha256:54f46433e32dbc10ef9d844c914d1d5f7ea03bf807e2ef3b407fd4b0544c12aa"],"state_sha256":"169d8aaf3dc6e084df2e4f3da6025dcf0e30d0690041551efb48937f790c8560"}