{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PJLZFXCKDRZNNRYAF4LTJS5QEY","short_pith_number":"pith:PJLZFXCK","canonical_record":{"source":{"id":"2506.01850","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T16:38:50Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"ef0ee7ec53ac246407aec243613e2dd0f73f64dadce4578eb57ab3535a4ce565","abstract_canon_sha256":"600ec099a8c2becdf0e09be6f4c84c2ef450f79342355453c863ace9ce50a765"},"schema_version":"1.0"},"canonical_sha256":"7a5792dc4a1c72d6c7002f1734cbb0262025bce42dea8c48f3c8967c4355b6a4","source":{"kind":"arxiv","id":"2506.01850","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01850","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01850v2","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01850","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"PJLZFXCKDRZN","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"PJLZFXCKDRZNNRYA","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"PJLZFXCK","created_at":"2026-06-08T01:03:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PJLZFXCKDRZNNRYAF4LTJS5QEY","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01850","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T16:38:50Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"ef0ee7ec53ac246407aec243613e2dd0f73f64dadce4578eb57ab3535a4ce565","abstract_canon_sha256":"600ec099a8c2becdf0e09be6f4c84c2ef450f79342355453c863ace9ce50a765"},"schema_version":"1.0"},"canonical_sha256":"7a5792dc4a1c72d6c7002f1734cbb0262025bce42dea8c48f3c8967c4355b6a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:45.355894Z","signature_b64":"uzFRBChIjbE2CFEU7FJ7pJmFyV60nznyYq9uvZQED3zwWRNGiSzqtPEd4UW3K/So75pfZgyliWzsLG5+HaIpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a5792dc4a1c72d6c7002f1734cbb0262025bce42dea8c48f3c8967c4355b6a4","last_reissued_at":"2026-06-08T01:03:45.355041Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:45.355041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01850","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":"2026-06-08T01:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WxAIqflobchHP7blmGzDJg+nlbuO2A+R7c48hm2fqw+W/oOon1RMuoKOHjU230TDpwKFy+GX45xW6aXa8MTlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T23:55:03.038440Z"},"content_sha256":"f57abd309dc7420af61c7822c7fda243eeef90636892a83f55c7cb1708533c63","schema_version":"1.0","event_id":"sha256:f57abd309dc7420af61c7822c7fda243eeef90636892a83f55c7cb1708533c63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PJLZFXCKDRZNNRYAF4LTJS5QEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Andr\\'es Villa, Bernard Ghanem, Juan Le\\'on Alc\\'azar, SouYoung Jin, Wayner Barrios","submitted_at":"2025-06-02T16:38:50Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable success in instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often struggle with fine-grained visual grounding due to semantic entanglement in visual patch representations, where individual patches blend multiple distinct visual elements, making it difficult for models to focus on instruction-relevant details. To address this challenge, we propose MoDA (Modulation Adapter), a lightweight module that enhances visual grounding through instruction-g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01850","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/2506.01850/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":"2026-06-08T01:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VsI7OrgpFE1RW2KQOamxsa779ftQTz6mqoApItXvYeic68oXNORSqqygn5WjC5DsgM2gXuhEEQf6vcFhS2CnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T23:55:03.038819Z"},"content_sha256":"bbaa6796bcaaa3603387eb075b8c1f5b0dd15928b1a772099ca60d97a8836531","schema_version":"1.0","event_id":"sha256:bbaa6796bcaaa3603387eb075b8c1f5b0dd15928b1a772099ca60d97a8836531"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/bundle.json","state_url":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/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":"2026-06-25T23:55:03Z","links":{"resolver":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY","bundle":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/bundle.json","state":"https://pith.science/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJLZFXCKDRZNNRYAF4LTJS5QEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PJLZFXCKDRZNNRYAF4LTJS5QEY","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":"600ec099a8c2becdf0e09be6f4c84c2ef450f79342355453c863ace9ce50a765","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T16:38:50Z","title_canon_sha256":"ef0ee7ec53ac246407aec243613e2dd0f73f64dadce4578eb57ab3535a4ce565"},"schema_version":"1.0","source":{"id":"2506.01850","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01850","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01850v2","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01850","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"PJLZFXCKDRZN","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"PJLZFXCKDRZNNRYA","created_at":"2026-06-08T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"PJLZFXCK","created_at":"2026-06-08T01:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:bbaa6796bcaaa3603387eb075b8c1f5b0dd15928b1a772099ca60d97a8836531","target":"graph","created_at":"2026-06-08T01:03:45Z","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/2506.01850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable success in instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often struggle with fine-grained visual grounding due to semantic entanglement in visual patch representations, where individual patches blend multiple distinct visual elements, making it difficult for models to focus on instruction-relevant details. To address this challenge, we propose MoDA (Modulation Adapter), a lightweight module that enhances visual grounding through instruction-g","authors_text":"Andr\\'es Villa, Bernard Ghanem, Juan Le\\'on Alc\\'azar, SouYoung Jin, Wayner Barrios","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T16:38:50Z","title":"MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01850","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:f57abd309dc7420af61c7822c7fda243eeef90636892a83f55c7cb1708533c63","target":"record","created_at":"2026-06-08T01:03:45Z","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":"600ec099a8c2becdf0e09be6f4c84c2ef450f79342355453c863ace9ce50a765","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T16:38:50Z","title_canon_sha256":"ef0ee7ec53ac246407aec243613e2dd0f73f64dadce4578eb57ab3535a4ce565"},"schema_version":"1.0","source":{"id":"2506.01850","kind":"arxiv","version":2}},"canonical_sha256":"7a5792dc4a1c72d6c7002f1734cbb0262025bce42dea8c48f3c8967c4355b6a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a5792dc4a1c72d6c7002f1734cbb0262025bce42dea8c48f3c8967c4355b6a4","first_computed_at":"2026-06-08T01:03:45.355041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:45.355041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uzFRBChIjbE2CFEU7FJ7pJmFyV60nznyYq9uvZQED3zwWRNGiSzqtPEd4UW3K/So75pfZgyliWzsLG5+HaIpAg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:45.355894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01850","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f57abd309dc7420af61c7822c7fda243eeef90636892a83f55c7cb1708533c63","sha256:bbaa6796bcaaa3603387eb075b8c1f5b0dd15928b1a772099ca60d97a8836531"],"state_sha256":"55ddabcd1d273a8b5d59630ac6e23e653c0fe38b80a6e0f13a3ba7d252f1f373"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tiEaK9iRwwgyIKYdohjoT+gTFFI4s97P+zXOnpkNp1ppI3oRc+1Bc9HZ5ZNRHzj5McFjw4WD8JjiESiF/ykpBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T23:55:03.040911Z","bundle_sha256":"b240aa393e07a818e44cea07a5bc7756d865ef1613e82ebb801a58458f82e606"}}