{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G4VYFNWQN3ARNITW6DOUQN5HW3","short_pith_number":"pith:G4VYFNWQ","canonical_record":{"source":{"id":"2410.17146","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T16:26:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"54cdfe0acfd5399448fef7e25c489fab4f605959a6f63e94d64ba516255b7ba2","abstract_canon_sha256":"8c32e3bb57dccfdf1e753f98cf11ea81adfacd774952e5350e1b74cdabf6c244"},"schema_version":"1.0"},"canonical_sha256":"372b82b6d06ec116a276f0dd4837a7b6d14354dc708f33c98f798f5ccfb98d21","source":{"kind":"arxiv","id":"2410.17146","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17146","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17146v2","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17146","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"G4VYFNWQN3AR","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"G4VYFNWQN3ARNITW","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"G4VYFNWQ","created_at":"2026-07-05T10:21:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G4VYFNWQN3ARNITW6DOUQN5HW3","target":"record","payload":{"canonical_record":{"source":{"id":"2410.17146","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T16:26:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"54cdfe0acfd5399448fef7e25c489fab4f605959a6f63e94d64ba516255b7ba2","abstract_canon_sha256":"8c32e3bb57dccfdf1e753f98cf11ea81adfacd774952e5350e1b74cdabf6c244"},"schema_version":"1.0"},"canonical_sha256":"372b82b6d06ec116a276f0dd4837a7b6d14354dc708f33c98f798f5ccfb98d21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:25.189296Z","signature_b64":"G6EdtqP/4kDBrFCX8Bv2V0Ley0p7O1vfpbEqE1y9ZPXvIjy/A9gEYY9+4VRi2QFRdP4ZIDKuGDDAocDdybzUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"372b82b6d06ec116a276f0dd4837a7b6d14354dc708f33c98f798f5ccfb98d21","last_reissued_at":"2026-07-05T10:21:25.188766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:25.188766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.17146","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":"2026-07-05T10:21:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZRtw/Hlc/51YcKzfbw2AkSZkBmZ+rlgE95YoBhFgnHr0248sxyoSWc+aAfOf78RYzz7VQhjECro7yq4AOF6nDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:20:01.764015Z"},"content_sha256":"c0acf3068092d608bc0939db5768190c50a6485fe444661ade894f9592a5a324","schema_version":"1.0","event_id":"sha256:c0acf3068092d608bc0939db5768190c50a6485fe444661ade894f9592a5a324"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G4VYFNWQN3ARNITW6DOUQN5HW3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alessandro Favero, Francois Fleuret, Guillermo Ortiz-Jimenez, Ke Wang, Nikolaos Dimitriadis, Pascal Frossard","submitted_at":"2024-10-22T16:26:05Z","abstract_excerpt":"Fine-tuning pre-trained models has become the standard approach to endow them with specialized knowledge, but it poses fundamental challenges. In particular, \\textit{(i)} fine-tuning often leads to catastrophic forgetting, where improvements on a target domain degrade generalization on other tasks, and \\textit{(ii)} merging fine-tuned checkpoints from disparate tasks can lead to significant performance loss. To address these challenges, we introduce LiNeS, Layer-increasing Network Scaling, a post-training editing technique designed to preserve pre-trained generalization while enhancing fine-tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17146","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/2410.17146/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":"2026-07-05T10:21:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jdIZNadHA2HnkR/pg84765WntPn87DWazZ1kaU3Z4ddyvFE3X7tgym/ThbzClYWhMz4CPA6/URI1jRnWj9j/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:20:01.765328Z"},"content_sha256":"30358c5784cf5747513b55c8fbf0836963e4140537948316ce68286d8b9a837c","schema_version":"1.0","event_id":"sha256:30358c5784cf5747513b55c8fbf0836963e4140537948316ce68286d8b9a837c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4VYFNWQN3ARNITW6DOUQN5HW3/bundle.json","state_url":"https://pith.science/pith/G4VYFNWQN3ARNITW6DOUQN5HW3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4VYFNWQN3ARNITW6DOUQN5HW3/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":"2026-08-10T20:20:01Z","links":{"resolver":"https://pith.science/pith/G4VYFNWQN3ARNITW6DOUQN5HW3","bundle":"https://pith.science/pith/G4VYFNWQN3ARNITW6DOUQN5HW3/bundle.json","state":"https://pith.science/pith/G4VYFNWQN3ARNITW6DOUQN5HW3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4VYFNWQN3ARNITW6DOUQN5HW3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G4VYFNWQN3ARNITW6DOUQN5HW3","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":"8c32e3bb57dccfdf1e753f98cf11ea81adfacd774952e5350e1b74cdabf6c244","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T16:26:05Z","title_canon_sha256":"54cdfe0acfd5399448fef7e25c489fab4f605959a6f63e94d64ba516255b7ba2"},"schema_version":"1.0","source":{"id":"2410.17146","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17146","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17146v2","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17146","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"G4VYFNWQN3AR","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"G4VYFNWQN3ARNITW","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"G4VYFNWQ","created_at":"2026-07-05T10:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:30358c5784cf5747513b55c8fbf0836963e4140537948316ce68286d8b9a837c","target":"graph","created_at":"2026-07-05T10:21:25Z","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/2410.17146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pre-trained models has become the standard approach to endow them with specialized knowledge, but it poses fundamental challenges. In particular, \\textit{(i)} fine-tuning often leads to catastrophic forgetting, where improvements on a target domain degrade generalization on other tasks, and \\textit{(ii)} merging fine-tuned checkpoints from disparate tasks can lead to significant performance loss. To address these challenges, we introduce LiNeS, Layer-increasing Network Scaling, a post-training editing technique designed to preserve pre-trained generalization while enhancing fine-tu","authors_text":"Alessandro Favero, Francois Fleuret, Guillermo Ortiz-Jimenez, Ke Wang, Nikolaos Dimitriadis, Pascal Frossard","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T16:26:05Z","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17146","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:c0acf3068092d608bc0939db5768190c50a6485fe444661ade894f9592a5a324","target":"record","created_at":"2026-07-05T10:21:25Z","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":"8c32e3bb57dccfdf1e753f98cf11ea81adfacd774952e5350e1b74cdabf6c244","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T16:26:05Z","title_canon_sha256":"54cdfe0acfd5399448fef7e25c489fab4f605959a6f63e94d64ba516255b7ba2"},"schema_version":"1.0","source":{"id":"2410.17146","kind":"arxiv","version":2}},"canonical_sha256":"372b82b6d06ec116a276f0dd4837a7b6d14354dc708f33c98f798f5ccfb98d21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"372b82b6d06ec116a276f0dd4837a7b6d14354dc708f33c98f798f5ccfb98d21","first_computed_at":"2026-07-05T10:21:25.188766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:25.188766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G6EdtqP/4kDBrFCX8Bv2V0Ley0p7O1vfpbEqE1y9ZPXvIjy/A9gEYY9+4VRi2QFRdP4ZIDKuGDDAocDdybzUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:25.189296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17146","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0acf3068092d608bc0939db5768190c50a6485fe444661ade894f9592a5a324","sha256:30358c5784cf5747513b55c8fbf0836963e4140537948316ce68286d8b9a837c"],"state_sha256":"572d6825c3479ff6a53347190344813a5a6404d63d29ad2e3547d6d468e5179b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmO7a7F8VoqNSNwg7p+lWhy54ExDHTQ8/wbAjjMi6wiNXh+y/FpUTahaUNVI21PKKbxup1G8rexQ/9LCynqCAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:20:01.775026Z","bundle_sha256":"e5543ccbf13c2287e6e446010a14e3d6a61bf4769fb536ac3bf0c425399522da"}}