{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3EUPNWJMCKOYRD54TKXBBR4TYT","short_pith_number":"pith:3EUPNWJM","canonical_record":{"source":{"id":"2503.03321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:55:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d49c75759adac4e570122587e2dcb1d1a11a158aef8706afad3188409564f00","abstract_canon_sha256":"6cdc09a6dd47039c3441bd86870376b745b11c168ffa4f38ae9719e8be62d627"},"schema_version":"1.0"},"canonical_sha256":"d928f6d92c129d888fbc9aae10c793c4c5ff0f8b102e070652a4f30456a76311","source":{"kind":"arxiv","id":"2503.03321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03321","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03321v1","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03321","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"pith_short_12","alias_value":"3EUPNWJMCKOY","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"pith_short_16","alias_value":"3EUPNWJMCKOYRD54","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"pith_short_8","alias_value":"3EUPNWJM","created_at":"2026-07-05T10:24:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3EUPNWJMCKOYRD54TKXBBR4TYT","target":"record","payload":{"canonical_record":{"source":{"id":"2503.03321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:55:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d49c75759adac4e570122587e2dcb1d1a11a158aef8706afad3188409564f00","abstract_canon_sha256":"6cdc09a6dd47039c3441bd86870376b745b11c168ffa4f38ae9719e8be62d627"},"schema_version":"1.0"},"canonical_sha256":"d928f6d92c129d888fbc9aae10c793c4c5ff0f8b102e070652a4f30456a76311","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:43.335254Z","signature_b64":"1cwhZW3gjynjaKgw7OGmN9UgBERuji+8+TP9XnNyrDmvSgSfyTfVdVLEPs9it2Gmg1ZBZFvF6AwCm/OJy4u+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d928f6d92c129d888fbc9aae10c793c4c5ff0f8b102e070652a4f30456a76311","last_reissued_at":"2026-07-05T10:24:43.334728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:43.334728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.03321","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":"2026-07-05T10:24:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fgZUOTLUN2dck7rEHpF2yMhwqynGrW2FU6yxTBc83EVVy33lnogEH2kL0VlfCy4O/DQfvzkAzmU3PJXZEoYbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:47:17.087808Z"},"content_sha256":"855cacd9ab8b22a827355c4a926f720461f01fc7ab12fcdea8b4221b991ec25e","schema_version":"1.0","event_id":"sha256:855cacd9ab8b22a827355c4a926f720461f01fc7ab12fcdea8b4221b991ec25e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3EUPNWJMCKOYRD54TKXBBR4TYT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See What You Are Told: Visual Attention Sink in Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jinyeong Kim, Junhyeok Kim, Seil Kang, Seong Jae Hwang","submitted_at":"2025-03-05T09:55:07Z","abstract_excerpt":"Large multimodal models (LMMs) \"see\" images by leveraging the attention mechanism between text and visual tokens in the transformer decoder. Ideally, these models should focus on key visual information relevant to the text token. However, recent findings indicate that LMMs have an extraordinary tendency to consistently allocate high attention weights to specific visual tokens, even when these tokens are irrelevant to the corresponding text. In this study, we investigate the property behind the appearance of these irrelevant visual tokens and examine their characteristics. Our findings show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03321","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/2503.03321/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":"2026-07-05T10:24:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8e4vWnQ3a9dekhWz0yAV1Q+4i1r4XnfR+bj33flikfGSYZRMdZyHAwusG5CjoS+l5eHz5378EV0d/SmrsDGhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:47:17.088452Z"},"content_sha256":"a2a163ab22544567aa151153cebcc314f170ad38571c089a5159ea204761ea50","schema_version":"1.0","event_id":"sha256:a2a163ab22544567aa151153cebcc314f170ad38571c089a5159ea204761ea50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EUPNWJMCKOYRD54TKXBBR4TYT/bundle.json","state_url":"https://pith.science/pith/3EUPNWJMCKOYRD54TKXBBR4TYT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EUPNWJMCKOYRD54TKXBBR4TYT/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":"2026-07-07T14:47:17Z","links":{"resolver":"https://pith.science/pith/3EUPNWJMCKOYRD54TKXBBR4TYT","bundle":"https://pith.science/pith/3EUPNWJMCKOYRD54TKXBBR4TYT/bundle.json","state":"https://pith.science/pith/3EUPNWJMCKOYRD54TKXBBR4TYT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EUPNWJMCKOYRD54TKXBBR4TYT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3EUPNWJMCKOYRD54TKXBBR4TYT","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":"6cdc09a6dd47039c3441bd86870376b745b11c168ffa4f38ae9719e8be62d627","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:55:07Z","title_canon_sha256":"4d49c75759adac4e570122587e2dcb1d1a11a158aef8706afad3188409564f00"},"schema_version":"1.0","source":{"id":"2503.03321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03321","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03321v1","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03321","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"pith_short_12","alias_value":"3EUPNWJMCKOY","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"pith_short_16","alias_value":"3EUPNWJMCKOYRD54","created_at":"2026-07-05T10:24:43Z"},{"alias_kind":"pith_short_8","alias_value":"3EUPNWJM","created_at":"2026-07-05T10:24:43Z"}],"graph_snapshots":[{"event_id":"sha256:a2a163ab22544567aa151153cebcc314f170ad38571c089a5159ea204761ea50","target":"graph","created_at":"2026-07-05T10:24:43Z","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/2503.03321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal models (LMMs) \"see\" images by leveraging the attention mechanism between text and visual tokens in the transformer decoder. Ideally, these models should focus on key visual information relevant to the text token. However, recent findings indicate that LMMs have an extraordinary tendency to consistently allocate high attention weights to specific visual tokens, even when these tokens are irrelevant to the corresponding text. In this study, we investigate the property behind the appearance of these irrelevant visual tokens and examine their characteristics. Our findings show tha","authors_text":"Jinyeong Kim, Junhyeok Kim, Seil Kang, Seong Jae Hwang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:55:07Z","title":"See What You Are Told: Visual Attention Sink in Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03321","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":"sha256:855cacd9ab8b22a827355c4a926f720461f01fc7ab12fcdea8b4221b991ec25e","target":"record","created_at":"2026-07-05T10:24:43Z","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":"6cdc09a6dd47039c3441bd86870376b745b11c168ffa4f38ae9719e8be62d627","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T09:55:07Z","title_canon_sha256":"4d49c75759adac4e570122587e2dcb1d1a11a158aef8706afad3188409564f00"},"schema_version":"1.0","source":{"id":"2503.03321","kind":"arxiv","version":1}},"canonical_sha256":"d928f6d92c129d888fbc9aae10c793c4c5ff0f8b102e070652a4f30456a76311","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d928f6d92c129d888fbc9aae10c793c4c5ff0f8b102e070652a4f30456a76311","first_computed_at":"2026-07-05T10:24:43.334728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:43.334728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1cwhZW3gjynjaKgw7OGmN9UgBERuji+8+TP9XnNyrDmvSgSfyTfVdVLEPs9it2Gmg1ZBZFvF6AwCm/OJy4u+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:43.335254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:855cacd9ab8b22a827355c4a926f720461f01fc7ab12fcdea8b4221b991ec25e","sha256:a2a163ab22544567aa151153cebcc314f170ad38571c089a5159ea204761ea50"],"state_sha256":"e455483e0b8adf8c7948df1357c1d2e796eef9dd5e1ee2f991f613b3be613342"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2BLfR8tn93NfsOt9fFYL8GdcLjazDAJ6tUKMdhGjQFFKWQWeDXjV23VM9l+ab7dxz0zGOgtTvND8DavNkSsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:47:17.091404Z","bundle_sha256":"2d3496bbcd575b0e2aebd388a274e1427733cd928d97cc15c320a959a6a0dfc0"}}