{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WN4NYAUMHMAXSTCTR65NGNGPVR","short_pith_number":"pith:WN4NYAUM","canonical_record":{"source":{"id":"2502.01419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T14:58:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5605280e79c7f72bcf0ec540d408c8c73c461941637e1ade066e863f815526e","abstract_canon_sha256":"cd4ede834370d6cb78cb16237021a691c2647a42599eb18e0f0fe9e13e355e31"},"schema_version":"1.0"},"canonical_sha256":"b378dc028c3b01794c538fbad334cfac60b693196ed9a7efe3510f2fc7aa692c","source":{"kind":"arxiv","id":"2502.01419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01419","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01419v2","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01419","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"WN4NYAUMHMAX","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"WN4NYAUMHMAXSTCT","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"WN4NYAUM","created_at":"2026-07-05T11:15:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WN4NYAUMHMAXSTCTR65NGNGPVR","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T14:58:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5605280e79c7f72bcf0ec540d408c8c73c461941637e1ade066e863f815526e","abstract_canon_sha256":"cd4ede834370d6cb78cb16237021a691c2647a42599eb18e0f0fe9e13e355e31"},"schema_version":"1.0"},"canonical_sha256":"b378dc028c3b01794c538fbad334cfac60b693196ed9a7efe3510f2fc7aa692c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:42.475090Z","signature_b64":"Zg4BXvsGDTEMuA7maUL2MKLYpf3kEZVS4h+A5cVEqmaLrHxkLAhdqjFO4wony6Q3rikt+l2Y8hbmjLg0tuLZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b378dc028c3b01794c538fbad334cfac60b693196ed9a7efe3510f2fc7aa692c","last_reissued_at":"2026-07-05T11:15:42.474672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:42.474672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01419","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":"2026-07-05T11:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GtWHRLZMwcsvVywcEgFg5esp8HepG52XbBX8/whZBNIkA5YPA9BhYYDOS2AQOPvU8emXa3K2tMM6C11H/th7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:02:21.441285Z"},"content_sha256":"ab11860f3d937eb48d48ac770485701a5735565f2d80fa4a3bca8ebc62412d91","schema_version":"1.0","event_id":"sha256:ab11860f3d937eb48d48ac770485701a5735565f2d80fa4a3bca8ebc62412d91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WN4NYAUMHMAXSTCTR65NGNGPVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Eunji Kim, Mingi Jung, Saehyung Lee, Sungroh Yoon","submitted_at":"2025-02-03T14:58:11Z","abstract_excerpt":"Detailed image captioning is essential for tasks like data generation and aiding visually impaired individuals. High-quality captions require a balance between precision and recall, which remains challenging for current multimodal large language models (MLLMs). In this work, we hypothesize that this limitation stems from weakening and increasingly noisy visual attention as responses lengthen. To address this issue, we propose SPARC (Selective Progressive Attention ReCalibration), a training-free method that enhances the contribution of visual tokens during decoding. SPARC is founded on three k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01419","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/2502.01419/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":"2026-07-05T11:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZFuOWnblB7qtljSQN77wQq1ky9Twa/xDZdkbYP8i5tPuc8JgZsQEKyvDWYdZgNBierQeW4ncR+oPLAsSqJeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:02:21.441935Z"},"content_sha256":"632426bd3af0a2b8fc5aee7c09aa87e7fb698c6f7c1d96db4ab67981c986762f","schema_version":"1.0","event_id":"sha256:632426bd3af0a2b8fc5aee7c09aa87e7fb698c6f7c1d96db4ab67981c986762f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WN4NYAUMHMAXSTCTR65NGNGPVR/bundle.json","state_url":"https://pith.science/pith/WN4NYAUMHMAXSTCTR65NGNGPVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WN4NYAUMHMAXSTCTR65NGNGPVR/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":"2026-08-04T19:02:21Z","links":{"resolver":"https://pith.science/pith/WN4NYAUMHMAXSTCTR65NGNGPVR","bundle":"https://pith.science/pith/WN4NYAUMHMAXSTCTR65NGNGPVR/bundle.json","state":"https://pith.science/pith/WN4NYAUMHMAXSTCTR65NGNGPVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WN4NYAUMHMAXSTCTR65NGNGPVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WN4NYAUMHMAXSTCTR65NGNGPVR","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":"cd4ede834370d6cb78cb16237021a691c2647a42599eb18e0f0fe9e13e355e31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T14:58:11Z","title_canon_sha256":"f5605280e79c7f72bcf0ec540d408c8c73c461941637e1ade066e863f815526e"},"schema_version":"1.0","source":{"id":"2502.01419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01419","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01419v2","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01419","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"WN4NYAUMHMAX","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"WN4NYAUMHMAXSTCT","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"WN4NYAUM","created_at":"2026-07-05T11:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:632426bd3af0a2b8fc5aee7c09aa87e7fb698c6f7c1d96db4ab67981c986762f","target":"graph","created_at":"2026-07-05T11:15:42Z","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/2502.01419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detailed image captioning is essential for tasks like data generation and aiding visually impaired individuals. High-quality captions require a balance between precision and recall, which remains challenging for current multimodal large language models (MLLMs). In this work, we hypothesize that this limitation stems from weakening and increasingly noisy visual attention as responses lengthen. To address this issue, we propose SPARC (Selective Progressive Attention ReCalibration), a training-free method that enhances the contribution of visual tokens during decoding. SPARC is founded on three k","authors_text":"Eunji Kim, Mingi Jung, Saehyung Lee, Sungroh Yoon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T14:58:11Z","title":"Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01419","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:ab11860f3d937eb48d48ac770485701a5735565f2d80fa4a3bca8ebc62412d91","target":"record","created_at":"2026-07-05T11:15:42Z","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":"cd4ede834370d6cb78cb16237021a691c2647a42599eb18e0f0fe9e13e355e31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T14:58:11Z","title_canon_sha256":"f5605280e79c7f72bcf0ec540d408c8c73c461941637e1ade066e863f815526e"},"schema_version":"1.0","source":{"id":"2502.01419","kind":"arxiv","version":2}},"canonical_sha256":"b378dc028c3b01794c538fbad334cfac60b693196ed9a7efe3510f2fc7aa692c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b378dc028c3b01794c538fbad334cfac60b693196ed9a7efe3510f2fc7aa692c","first_computed_at":"2026-07-05T11:15:42.474672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:42.474672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zg4BXvsGDTEMuA7maUL2MKLYpf3kEZVS4h+A5cVEqmaLrHxkLAhdqjFO4wony6Q3rikt+l2Y8hbmjLg0tuLZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:42.475090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab11860f3d937eb48d48ac770485701a5735565f2d80fa4a3bca8ebc62412d91","sha256:632426bd3af0a2b8fc5aee7c09aa87e7fb698c6f7c1d96db4ab67981c986762f"],"state_sha256":"251adcce672b8bf5b2dd401f1b6ab29dc8988c4c078a8664591c76e71ea2ed37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86RH9ZLvA2rj71iXGqZ1TdVRofgYk64k0Mvxc8JbB/G0BhKlzKuTwz7r0vz4qlVD01fRfhI7Z4SiVzeyDcrhBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:02:21.445466Z","bundle_sha256":"1fd37905e98492d48977370462757199850b9f8fa172d86a5de55a751ea432fc"}}