{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HJSK6ALOZCIEKEKBSLAPCW75Q6","short_pith_number":"pith:HJSK6ALO","canonical_record":{"source":{"id":"2501.13904","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T18:34:09Z","cross_cats_sorted":[],"title_canon_sha256":"caedb2b0eb268ad371a45d77c656621d8bf7078f44ae2983c79d5749ff03f9ed","abstract_canon_sha256":"b708cb86e8207af6936d03bf952e46056a98049ebce60faeb608630c18279b95"},"schema_version":"1.0"},"canonical_sha256":"3a64af016ec89045114192c0f15bfd87848b94e16208c3b1f04d59edf61a498e","source":{"kind":"arxiv","id":"2501.13904","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13904","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13904v3","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13904","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"HJSK6ALOZCIE","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"HJSK6ALOZCIEKEKB","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"HJSK6ALO","created_at":"2026-07-05T10:13:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HJSK6ALOZCIEKEKBSLAPCW75Q6","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13904","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T18:34:09Z","cross_cats_sorted":[],"title_canon_sha256":"caedb2b0eb268ad371a45d77c656621d8bf7078f44ae2983c79d5749ff03f9ed","abstract_canon_sha256":"b708cb86e8207af6936d03bf952e46056a98049ebce60faeb608630c18279b95"},"schema_version":"1.0"},"canonical_sha256":"3a64af016ec89045114192c0f15bfd87848b94e16208c3b1f04d59edf61a498e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:46.550374Z","signature_b64":"r5wEoEClchzTYb5BMt65up8ZcFRWlvEL9WmXCZS1pp6Wei6TUawB7AH6UcoOWGCVDOg0pj6roBp1UTMIxwWnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a64af016ec89045114192c0f15bfd87848b94e16208c3b1f04d59edf61a498e","last_reissued_at":"2026-07-05T10:13:46.549894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:46.549894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13904","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+7iLmsCtYTrp3BkYwvAWW/EXuWJjLY9DgZtpiUdWMo92NsNDFxlTqjLu3fjYPwFT082zHTO19Y/4C2gJaI2XCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:49:39.086526Z"},"content_sha256":"b856f9eda25f336dfd502de6546f891c9416099381393bb8f605ba516dc5ba38","schema_version":"1.0","event_id":"sha256:b856f9eda25f336dfd502de6546f891c9416099381393bb8f605ba516dc5ba38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HJSK6ALOZCIEKEKBSLAPCW75Q6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ana Milanova, Linh Tran, Stacy Patterson, Wei Sun","submitted_at":"2025-01-23T18:34:09Z","abstract_excerpt":"Multimodal Large Language Models (LLMs) are pivotal in revolutionizing customer support and operations by integrating multiple modalities such as text, images, and audio. Federated Prompt Learning (FPL) is a recently proposed approach that combines pre-trained multimodal LLMs such as vision-language models with federated learning to create personalized, privacy-preserving AI systems. However, balancing the competing goals of personalization, generalization, and privacy remains a significant challenge. Over-personalization can lead to overfitting, reducing generalizability, while stringent priv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13904","kind":"arxiv","version":3},"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/2501.13904/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":"2026-07-05T10:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vHOtYo/tUQib10i9HBTKicXrxYy82ZPDqOCQuQgJ43l+zvHzskYW58RwWCQgmubmT3ahEMk/lUwh6odltezBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:49:39.087036Z"},"content_sha256":"b5cb1611cc6164c83c791814d7e38cd64e0cde6fa71cfc6acba5228c8e0a30fa","schema_version":"1.0","event_id":"sha256:b5cb1611cc6164c83c791814d7e38cd64e0cde6fa71cfc6acba5228c8e0a30fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJSK6ALOZCIEKEKBSLAPCW75Q6/bundle.json","state_url":"https://pith.science/pith/HJSK6ALOZCIEKEKBSLAPCW75Q6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJSK6ALOZCIEKEKBSLAPCW75Q6/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":"2026-08-10T18:49:39Z","links":{"resolver":"https://pith.science/pith/HJSK6ALOZCIEKEKBSLAPCW75Q6","bundle":"https://pith.science/pith/HJSK6ALOZCIEKEKBSLAPCW75Q6/bundle.json","state":"https://pith.science/pith/HJSK6ALOZCIEKEKBSLAPCW75Q6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJSK6ALOZCIEKEKBSLAPCW75Q6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HJSK6ALOZCIEKEKBSLAPCW75Q6","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":"b708cb86e8207af6936d03bf952e46056a98049ebce60faeb608630c18279b95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T18:34:09Z","title_canon_sha256":"caedb2b0eb268ad371a45d77c656621d8bf7078f44ae2983c79d5749ff03f9ed"},"schema_version":"1.0","source":{"id":"2501.13904","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13904","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13904v3","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13904","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"HJSK6ALOZCIE","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"HJSK6ALOZCIEKEKB","created_at":"2026-07-05T10:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"HJSK6ALO","created_at":"2026-07-05T10:13:46Z"}],"graph_snapshots":[{"event_id":"sha256:b5cb1611cc6164c83c791814d7e38cd64e0cde6fa71cfc6acba5228c8e0a30fa","target":"graph","created_at":"2026-07-05T10:13:46Z","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/2501.13904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (LLMs) are pivotal in revolutionizing customer support and operations by integrating multiple modalities such as text, images, and audio. Federated Prompt Learning (FPL) is a recently proposed approach that combines pre-trained multimodal LLMs such as vision-language models with federated learning to create personalized, privacy-preserving AI systems. However, balancing the competing goals of personalization, generalization, and privacy remains a significant challenge. Over-personalization can lead to overfitting, reducing generalizability, while stringent priv","authors_text":"Ana Milanova, Linh Tran, Stacy Patterson, Wei Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T18:34:09Z","title":"Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13904","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:b856f9eda25f336dfd502de6546f891c9416099381393bb8f605ba516dc5ba38","target":"record","created_at":"2026-07-05T10:13:46Z","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":"b708cb86e8207af6936d03bf952e46056a98049ebce60faeb608630c18279b95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T18:34:09Z","title_canon_sha256":"caedb2b0eb268ad371a45d77c656621d8bf7078f44ae2983c79d5749ff03f9ed"},"schema_version":"1.0","source":{"id":"2501.13904","kind":"arxiv","version":3}},"canonical_sha256":"3a64af016ec89045114192c0f15bfd87848b94e16208c3b1f04d59edf61a498e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a64af016ec89045114192c0f15bfd87848b94e16208c3b1f04d59edf61a498e","first_computed_at":"2026-07-05T10:13:46.549894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:46.549894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r5wEoEClchzTYb5BMt65up8ZcFRWlvEL9WmXCZS1pp6Wei6TUawB7AH6UcoOWGCVDOg0pj6roBp1UTMIxwWnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:46.550374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13904","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b856f9eda25f336dfd502de6546f891c9416099381393bb8f605ba516dc5ba38","sha256:b5cb1611cc6164c83c791814d7e38cd64e0cde6fa71cfc6acba5228c8e0a30fa"],"state_sha256":"0a279e665f5f14c465e449287567b90eee5896002b562c82e312a6be582898bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0FGyWLSpjJzBvU/4t3KNCq6kXOB73RiChdA7SUugLBrxM121qJY40Nj+iN2gS2oAKTh1T+WfJGYsXo8In9VDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:49:39.092184Z","bundle_sha256":"8acfbe4fbbae8e818e497e6b20106594b10f64b2248aae361e1f70057377b134"}}