{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GJMK4BY6MWD3AQ3IJQBYH7LHIL","short_pith_number":"pith:GJMK4BY6","canonical_record":{"source":{"id":"2502.12420","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T01:41:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c29ff663390c05ac7cc4b54fd2f40abee6e1f33c06d288298fa6ccadabc62e7","abstract_canon_sha256":"3a3be4b3bee06bbee8306efa620ae26148e4956b08bbf5b81e6c0a84d0f75fac"},"schema_version":"1.0"},"canonical_sha256":"3258ae071e6587b043684c0383fd6742c3bfa98eef24dd7299b6692eb428f531","source":{"kind":"arxiv","id":"2502.12420","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12420","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12420v2","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12420","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"pith_short_12","alias_value":"GJMK4BY6MWD3","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"pith_short_16","alias_value":"GJMK4BY6MWD3AQ3I","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"pith_short_8","alias_value":"GJMK4BY6","created_at":"2026-07-05T10:16:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GJMK4BY6MWD3AQ3IJQBYH7LHIL","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12420","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T01:41:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c29ff663390c05ac7cc4b54fd2f40abee6e1f33c06d288298fa6ccadabc62e7","abstract_canon_sha256":"3a3be4b3bee06bbee8306efa620ae26148e4956b08bbf5b81e6c0a84d0f75fac"},"schema_version":"1.0"},"canonical_sha256":"3258ae071e6587b043684c0383fd6742c3bfa98eef24dd7299b6692eb428f531","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:42.568856Z","signature_b64":"HaM7Ss22RH+rVhULBTfpsc9YZ+PliaAcK2KUforbZ5Xq7fI/9vxYINbufVLoYuoeMmlLYO68CZLijySK/pIBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3258ae071e6587b043684c0383fd6742c3bfa98eef24dd7299b6692eb428f531","last_reissued_at":"2026-07-05T10:16:42.568278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:42.568278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12420","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":"2026-07-05T10:16:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9pST0BrPqCbmUnwfFgqhT2831iCj9X3Xorr/8lJ7wGMPwkxsyTH4qaSUwgDuaXUDkXN5BvbCN0Im5UPGL+eCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:25:48.731259Z"},"content_sha256":"ee8d4d17786cfca6912e3c9ad287272815572880732b34c9a88d7c4686b682a9","schema_version":"1.0","event_id":"sha256:ee8d4d17786cfca6912e3c9ad287272815572880732b34c9a88d7c4686b682a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GJMK4BY6MWD3AQ3IJQBYH7LHIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowei He, Han Wu, Linqi Song, Mingxuan Yuan, Shuqi Liu, Xiongwei Han","submitted_at":"2025-02-18T01:41:13Z","abstract_excerpt":"Recent advances in large language models have led to numerous task-specialized fine-tuned variants, creating a need for efficient model merging techniques that preserve specialized capabilities while avoiding costly retraining. While existing task vector-based merging methods show promise, they typically apply uniform coefficients across all parameters, overlooking varying parameter importance both within and across tasks. We present Sens-Merging, a sensitivity-guided coefficient adjustment method that enhances existing model merging techniques by operating at both task-specific and cross-task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12420","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/2502.12420/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":"2026-07-05T10:16:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U56c2yyPX4JoP4OIowVLL14VQpYjN7a4hmhCfEt/Dk48+0eZrHAD8RNps64mhQHi2N9jGzSOeTEHOPMdyOhHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:25:48.731826Z"},"content_sha256":"b2073aa5d18f546db3bce98405824acf07e7eefcd2bf2e5e701e98620accdc98","schema_version":"1.0","event_id":"sha256:b2073aa5d18f546db3bce98405824acf07e7eefcd2bf2e5e701e98620accdc98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJMK4BY6MWD3AQ3IJQBYH7LHIL/bundle.json","state_url":"https://pith.science/pith/GJMK4BY6MWD3AQ3IJQBYH7LHIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJMK4BY6MWD3AQ3IJQBYH7LHIL/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":"2026-08-17T03:25:48Z","links":{"resolver":"https://pith.science/pith/GJMK4BY6MWD3AQ3IJQBYH7LHIL","bundle":"https://pith.science/pith/GJMK4BY6MWD3AQ3IJQBYH7LHIL/bundle.json","state":"https://pith.science/pith/GJMK4BY6MWD3AQ3IJQBYH7LHIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJMK4BY6MWD3AQ3IJQBYH7LHIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GJMK4BY6MWD3AQ3IJQBYH7LHIL","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":"3a3be4b3bee06bbee8306efa620ae26148e4956b08bbf5b81e6c0a84d0f75fac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T01:41:13Z","title_canon_sha256":"0c29ff663390c05ac7cc4b54fd2f40abee6e1f33c06d288298fa6ccadabc62e7"},"schema_version":"1.0","source":{"id":"2502.12420","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12420","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12420v2","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12420","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"pith_short_12","alias_value":"GJMK4BY6MWD3","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"pith_short_16","alias_value":"GJMK4BY6MWD3AQ3I","created_at":"2026-07-05T10:16:42Z"},{"alias_kind":"pith_short_8","alias_value":"GJMK4BY6","created_at":"2026-07-05T10:16:42Z"}],"graph_snapshots":[{"event_id":"sha256:b2073aa5d18f546db3bce98405824acf07e7eefcd2bf2e5e701e98620accdc98","target":"graph","created_at":"2026-07-05T10:16:42Z","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/2502.12420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models have led to numerous task-specialized fine-tuned variants, creating a need for efficient model merging techniques that preserve specialized capabilities while avoiding costly retraining. While existing task vector-based merging methods show promise, they typically apply uniform coefficients across all parameters, overlooking varying parameter importance both within and across tasks. We present Sens-Merging, a sensitivity-guided coefficient adjustment method that enhances existing model merging techniques by operating at both task-specific and cross-task","authors_text":"Bowei He, Han Wu, Linqi Song, Mingxuan Yuan, Shuqi Liu, Xiongwei Han","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T01:41:13Z","title":"Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12420","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:ee8d4d17786cfca6912e3c9ad287272815572880732b34c9a88d7c4686b682a9","target":"record","created_at":"2026-07-05T10:16:42Z","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":"3a3be4b3bee06bbee8306efa620ae26148e4956b08bbf5b81e6c0a84d0f75fac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T01:41:13Z","title_canon_sha256":"0c29ff663390c05ac7cc4b54fd2f40abee6e1f33c06d288298fa6ccadabc62e7"},"schema_version":"1.0","source":{"id":"2502.12420","kind":"arxiv","version":2}},"canonical_sha256":"3258ae071e6587b043684c0383fd6742c3bfa98eef24dd7299b6692eb428f531","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3258ae071e6587b043684c0383fd6742c3bfa98eef24dd7299b6692eb428f531","first_computed_at":"2026-07-05T10:16:42.568278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:42.568278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HaM7Ss22RH+rVhULBTfpsc9YZ+PliaAcK2KUforbZ5Xq7fI/9vxYINbufVLoYuoeMmlLYO68CZLijySK/pIBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:42.568856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12420","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee8d4d17786cfca6912e3c9ad287272815572880732b34c9a88d7c4686b682a9","sha256:b2073aa5d18f546db3bce98405824acf07e7eefcd2bf2e5e701e98620accdc98"],"state_sha256":"46a6bba57e829698472b7eb7ab4a4ec37b9c72f971cdc30cdbf4bb3551e81b02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lK1QztrIU4BN7pDhmI4XI71a9Cxxy3HOtt9lXoZi2hoLrdpxSe2B3dPc++NQ/c0grty9tBeWpJBgfdVWVjkCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T03:25:48.736592Z","bundle_sha256":"6464b81b7a3558bd7e561b3e94b8d699aa5d3668537026023a3b221fee95e0a3"}}