{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G5OQOZ47IT4DZUODCJA7TVSPZX","short_pith_number":"pith:G5OQOZ47","canonical_record":{"source":{"id":"2504.14662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:57:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"61430acc73f2701dc6149ddd1a9f805434888ad2b3b6e8802ad32819de208418","abstract_canon_sha256":"e5f02d05dce9a0d5c6b07ac43b0f22c2b7a724bd02d472744361ff56c18ed312"},"schema_version":"1.0"},"canonical_sha256":"375d07679f44f83cd1c31241f9d64fcdd1e0e2ddd7ca62994e486ba83374fcf5","source":{"kind":"arxiv","id":"2504.14662","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14662","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14662v1","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14662","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"G5OQOZ47IT4D","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"G5OQOZ47IT4DZUOD","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"G5OQOZ47","created_at":"2026-07-05T10:51:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G5OQOZ47IT4DZUODCJA7TVSPZX","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:57:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"61430acc73f2701dc6149ddd1a9f805434888ad2b3b6e8802ad32819de208418","abstract_canon_sha256":"e5f02d05dce9a0d5c6b07ac43b0f22c2b7a724bd02d472744361ff56c18ed312"},"schema_version":"1.0"},"canonical_sha256":"375d07679f44f83cd1c31241f9d64fcdd1e0e2ddd7ca62994e486ba83374fcf5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:48.479412Z","signature_b64":"F0hHNsPG6VsNqWHxQGXquPcguzCAEL9bDIe3QtjF+JSoNLbfL8ID9ATc9GBBrC5BMGzjrx7M7dsJTNijDJj1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375d07679f44f83cd1c31241f9d64fcdd1e0e2ddd7ca62994e486ba83374fcf5","last_reissued_at":"2026-07-05T10:51:48.478907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:48.478907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14662","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":"2026-07-05T10:51:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sRJMkyMeQURhbu1pTEUmJzBgJM2g3x+V3TH66SVExR22oBeH+lDkrC7c+WVfIg6B/Zbv4RMu1CZ6MugG6auMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:18:32.166501Z"},"content_sha256":"a21805f96ef9368931677697452776fa68db92fdffc8bfa8d4d3e7b8306b4835","schema_version":"1.0","event_id":"sha256:a21805f96ef9368931677697452776fa68db92fdffc8bfa8d4d3e7b8306b4835"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G5OQOZ47IT4DZUODCJA7TVSPZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jinwook Jung, Sungyong Baik, Yeoreum Lee","submitted_at":"2025-04-20T15:57:12Z","abstract_excerpt":"Large-scale deep learning models with a pretraining-finetuning paradigm have led to a surge of numerous task-specific models fine-tuned from a common pre-trained model. Recently, several research efforts have been made on merging these large models into a single multi-task model, particularly with simple arithmetic on parameters. Such merging methodology faces a central challenge: interference between model parameters fine-tuned on different tasks. Few recent works have focused on designing a new fine-tuning scheme that can lead to small parameter interference, however at the cost of the perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14662","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/2504.14662/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":"2026-07-05T10:51:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"teUGRjZhlJ/ALCyEWNYu68iZtZ3ycguFvSaBtu0doAGdpRVYwZHyn6k9JIfcrCsNMOVqaRxe2J/fApghX/zqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:18:32.167037Z"},"content_sha256":"e2f6037f56b6e5112ba25b7d3813d708cebb2d51dae91fb62e6e269c90eeb00d","schema_version":"1.0","event_id":"sha256:e2f6037f56b6e5112ba25b7d3813d708cebb2d51dae91fb62e6e269c90eeb00d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5OQOZ47IT4DZUODCJA7TVSPZX/bundle.json","state_url":"https://pith.science/pith/G5OQOZ47IT4DZUODCJA7TVSPZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5OQOZ47IT4DZUODCJA7TVSPZX/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":"2026-08-11T06:18:32Z","links":{"resolver":"https://pith.science/pith/G5OQOZ47IT4DZUODCJA7TVSPZX","bundle":"https://pith.science/pith/G5OQOZ47IT4DZUODCJA7TVSPZX/bundle.json","state":"https://pith.science/pith/G5OQOZ47IT4DZUODCJA7TVSPZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5OQOZ47IT4DZUODCJA7TVSPZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G5OQOZ47IT4DZUODCJA7TVSPZX","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":"e5f02d05dce9a0d5c6b07ac43b0f22c2b7a724bd02d472744361ff56c18ed312","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:57:12Z","title_canon_sha256":"61430acc73f2701dc6149ddd1a9f805434888ad2b3b6e8802ad32819de208418"},"schema_version":"1.0","source":{"id":"2504.14662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14662","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14662v1","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14662","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"G5OQOZ47IT4D","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"G5OQOZ47IT4DZUOD","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"G5OQOZ47","created_at":"2026-07-05T10:51:48Z"}],"graph_snapshots":[{"event_id":"sha256:e2f6037f56b6e5112ba25b7d3813d708cebb2d51dae91fb62e6e269c90eeb00d","target":"graph","created_at":"2026-07-05T10:51:48Z","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/2504.14662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale deep learning models with a pretraining-finetuning paradigm have led to a surge of numerous task-specific models fine-tuned from a common pre-trained model. Recently, several research efforts have been made on merging these large models into a single multi-task model, particularly with simple arithmetic on parameters. Such merging methodology faces a central challenge: interference between model parameters fine-tuned on different tasks. Few recent works have focused on designing a new fine-tuning scheme that can lead to small parameter interference, however at the cost of the perfo","authors_text":"Jinwook Jung, Sungyong Baik, Yeoreum Lee","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:57:12Z","title":"Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14662","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:a21805f96ef9368931677697452776fa68db92fdffc8bfa8d4d3e7b8306b4835","target":"record","created_at":"2026-07-05T10:51:48Z","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":"e5f02d05dce9a0d5c6b07ac43b0f22c2b7a724bd02d472744361ff56c18ed312","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:57:12Z","title_canon_sha256":"61430acc73f2701dc6149ddd1a9f805434888ad2b3b6e8802ad32819de208418"},"schema_version":"1.0","source":{"id":"2504.14662","kind":"arxiv","version":1}},"canonical_sha256":"375d07679f44f83cd1c31241f9d64fcdd1e0e2ddd7ca62994e486ba83374fcf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"375d07679f44f83cd1c31241f9d64fcdd1e0e2ddd7ca62994e486ba83374fcf5","first_computed_at":"2026-07-05T10:51:48.478907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:48.478907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F0hHNsPG6VsNqWHxQGXquPcguzCAEL9bDIe3QtjF+JSoNLbfL8ID9ATc9GBBrC5BMGzjrx7M7dsJTNijDJj1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:48.479412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a21805f96ef9368931677697452776fa68db92fdffc8bfa8d4d3e7b8306b4835","sha256:e2f6037f56b6e5112ba25b7d3813d708cebb2d51dae91fb62e6e269c90eeb00d"],"state_sha256":"679c11cafa101e2c03a2cd603194f51572736ff0de62083a72f4507c444d96b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M8WuxmXo+tQFkU7PduGM80o2SsiHdDIR2N52KqgkTOA4sIvEP6T3dvCjdRx5bXSfHThU7QV5wlFMvLYYBja3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T06:18:32.173631Z","bundle_sha256":"1b00f1e2cb778e2f32ca3ec2dd55e4f9ac6a3381ad9973a78c5948d1d536de30"}}