{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IAV6G2YDH3T4EJ7CEVYSCSLATN","short_pith_number":"pith:IAV6G2YD","canonical_record":{"source":{"id":"2605.18359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T13:12:50Z","cross_cats_sorted":[],"title_canon_sha256":"972a85dd5697e2acd03050f1944f51aee8ff1e8520d301d995baee358cc6d247","abstract_canon_sha256":"395011c5e02147d5d375607c403201e2822f812aa96bc103a0f17e9a20166450"},"schema_version":"1.0"},"canonical_sha256":"402be36b033ee7c227e225712149609b698ef952a4197737bf52a4ac25f5ad17","source":{"kind":"arxiv","id":"2605.18359","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18359","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18359v1","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18359","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"IAV6G2YDH3T4","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"IAV6G2YDH3T4EJ7C","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"IAV6G2YD","created_at":"2026-05-20T00:05:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IAV6G2YDH3T4EJ7CEVYSCSLATN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T13:12:50Z","cross_cats_sorted":[],"title_canon_sha256":"972a85dd5697e2acd03050f1944f51aee8ff1e8520d301d995baee358cc6d247","abstract_canon_sha256":"395011c5e02147d5d375607c403201e2822f812aa96bc103a0f17e9a20166450"},"schema_version":"1.0"},"canonical_sha256":"402be36b033ee7c227e225712149609b698ef952a4197737bf52a4ac25f5ad17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:56.984850Z","signature_b64":"1lf2z713ckTfG1pP2NmMceGCKXWpMan5B/UdcuL0txGEU+TkNLHVpzrwTZ0/+Hu0+Cel2hT42ODK9F2+47M4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"402be36b033ee7c227e225712149609b698ef952a4197737bf52a4ac25f5ad17","last_reissued_at":"2026-05-20T00:05:56.984077Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:56.984077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18359","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":"2026-05-20T00:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWs1OSKEOFgCn2IszreMrAghgKkwW+ITJ9OkNQbtNbLqZbNxWPPZ6zYWcqUiIrBITdid35hX+G+qOpUyOo64AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:28:44.609498Z"},"content_sha256":"761fe50770cb95506069e36838a43c9e0befaa516dfb40f2684c17308a559a07","schema_version":"1.0","event_id":"sha256:761fe50770cb95506069e36838a43c9e0befaa516dfb40f2684c17308a559a07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IAV6G2YDH3T4EJ7CEVYSCSLATN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAVE: Re-Allocating Visual Attention in Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhang, Guanjun Jiang, Xiaoying Tang, Xi Leng, Xinhong Ma, Yang Yang, Ziqiang Dong","submitted_at":"2026-05-18T13:12:50Z","abstract_excerpt":"Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and intra-visual imbalance among visual tokens. We propose RAVE (Re-Allocating Visual Attention), a lightweight pair-gating mechanism that adds a learned query--key bias to pre-softmax attention scores over visual keys, derived from pre-RoPE query and key features. RAVE requires no architectural modification to the backbone and can be trained end-to-end with the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18359","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/2605.18359/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:30.714805Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T23:31:52.366466Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.795121Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"04e48ff8d77638bb98e8574f93c6245d41fbd8931889ace5f3f3167df82d2869"},"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":"2026-05-20T00:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SRtvsn0YlxPRkHmA/NHa1RyaMeXKfvenypii2I0IrLD353/0sSEbsqos/OmNVZY52fjWUCSO9r+AIDfpN6m7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:28:44.610139Z"},"content_sha256":"043d141781028b58fac64e12e8763701472b9c134b3dad821b079ed55b89ac29","schema_version":"1.0","event_id":"sha256:043d141781028b58fac64e12e8763701472b9c134b3dad821b079ed55b89ac29"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:IAV6G2YDH3T4EJ7CEVYSCSLATN","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2025.findings-acl.404.URLhttps://aclanthology.org/2025.findings-acl.404/.Tu) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Tang, F., Liu, C., Xu, Z., Hu, M., Huang, Z., Xue, H., Chen, Z., Peng, Z., Yang, Z., Zhou, S., Li, W., Li, Y ., Song, W., Su, S., Feng, W., Su, J., Lin, M., Peng, Y ., Cheng, X., Razzak, I., and Ge, Z. Seeing far and clearly: Mitigating hal","arxiv_id":"2605.18359","detector":"doi_compliance","evidence":{"ref_index":8,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Tang, F., Liu, C., Xu, Z., Hu, M., Huang, Z., Xue, H., Chen, Z., Peng, Z., Yang, Z., Zhou, S., Li, W., Li, Y ., Song, W., Su, S., Feng, W., Su, J., Lin, M., Peng, Y ., Cheng, X., Razzak, I., and Ge, Z. Seeing far and clearly: Mitigating hal","reconstructed_doi":"10.18653/v1/2025.findings-acl.404.URLhttps://aclanthology.org/2025.findings-acl.404/.Tu"},"severity":"advisory","ref_index":8,"audited_at":"2026-05-20T11:12:24.033852Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2025.findings-acl.404.URLhttps://aclanthology.org/2025.findings-acl.404/.Tu","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"298141e35d3087c878ff3915f2424e652405d3dd9211299d2076fe320aff3b4b","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":5022,"payload_sha256":"79eedea37b663be4e0b2779dbadd65bceb275b3e493289019971f1703c19a3e1","signature_b64":"6ZXSXSB6TiLZRYZ6y3tepQTx9JO0igyRyS9DnlEXED9satwSXgQU5IK9CaIyK31gpjGDSxdDNS78naim7mR6BQ==","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":"2026-05-20T11:12:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7YChfiuWxWxB1pTsIHcyHv2SwmA4wPW1myPOA/lGJMhqqebBPSq2h3ZE9bEVAhOQIKXq8coA58IXlA0GJu0UCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:28:44.611233Z"},"content_sha256":"33ae286d5e48c74a7ec12c8eae0aee98a2dae50bf50e860a101ea4a3537cc2e8","schema_version":"1.0","event_id":"sha256:33ae286d5e48c74a7ec12c8eae0aee98a2dae50bf50e860a101ea4a3537cc2e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/bundle.json","state_url":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/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":"2026-05-21T12:28:44Z","links":{"resolver":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN","bundle":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/bundle.json","state":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IAV6G2YDH3T4EJ7CEVYSCSLATN","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":"395011c5e02147d5d375607c403201e2822f812aa96bc103a0f17e9a20166450","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T13:12:50Z","title_canon_sha256":"972a85dd5697e2acd03050f1944f51aee8ff1e8520d301d995baee358cc6d247"},"schema_version":"1.0","source":{"id":"2605.18359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18359","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18359v1","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18359","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"IAV6G2YDH3T4","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"IAV6G2YDH3T4EJ7C","created_at":"2026-05-20T00:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"IAV6G2YD","created_at":"2026-05-20T00:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:043d141781028b58fac64e12e8763701472b9c134b3dad821b079ed55b89ac29","target":"graph","created_at":"2026-05-20T00:05:56Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:30.714805Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"external_links","ran_at":"2026-05-19T23:31:52.366466Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.795121Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18359/integrity.json","findings":[],"snapshot_sha256":"04e48ff8d77638bb98e8574f93c6245d41fbd8931889ace5f3f3167df82d2869","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and intra-visual imbalance among visual tokens. We propose RAVE (Re-Allocating Visual Attention), a lightweight pair-gating mechanism that adds a learned query--key bias to pre-softmax attention scores over visual keys, derived from pre-RoPE query and key features. RAVE requires no architectural modification to the backbone and can be trained end-to-end with the res","authors_text":"Feng Zhang, Guanjun Jiang, Xiaoying Tang, Xi Leng, Xinhong Ma, Yang Yang, Ziqiang Dong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T13:12:50Z","title":"RAVE: Re-Allocating Visual Attention in Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18359","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":"sha256:761fe50770cb95506069e36838a43c9e0befaa516dfb40f2684c17308a559a07","target":"record","created_at":"2026-05-20T00:05:56Z","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":"395011c5e02147d5d375607c403201e2822f812aa96bc103a0f17e9a20166450","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T13:12:50Z","title_canon_sha256":"972a85dd5697e2acd03050f1944f51aee8ff1e8520d301d995baee358cc6d247"},"schema_version":"1.0","source":{"id":"2605.18359","kind":"arxiv","version":1}},"canonical_sha256":"402be36b033ee7c227e225712149609b698ef952a4197737bf52a4ac25f5ad17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"402be36b033ee7c227e225712149609b698ef952a4197737bf52a4ac25f5ad17","first_computed_at":"2026-05-20T00:05:56.984077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:56.984077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1lf2z713ckTfG1pP2NmMceGCKXWpMan5B/UdcuL0txGEU+TkNLHVpzrwTZ0/+Hu0+Cel2hT42ODK9F2+47M4Cg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:56.984850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:761fe50770cb95506069e36838a43c9e0befaa516dfb40f2684c17308a559a07","sha256:043d141781028b58fac64e12e8763701472b9c134b3dad821b079ed55b89ac29","sha256:33ae286d5e48c74a7ec12c8eae0aee98a2dae50bf50e860a101ea4a3537cc2e8"],"state_sha256":"3b06bfee35a3aea7fb0395c269141783089a3560f3997973e100635f18078056"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J7PSKyJoz4D/9AK/ZMz1C4g5jrn7EatDiQnuRWAqzomQYpQLmJyzLu36+I1Q1YkSemOFUxeHX9LegaHVkK94DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T12:28:44.614254Z","bundle_sha256":"c7c1b5b46b0a00c71882c7c6639aa2c978b3a99114a51234d0f1ae7b9b734707"}}