{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:D442P6UZFIGD2ZD3KLF777SMTF","short_pith_number":"pith:D442P6UZ","canonical_record":{"source":{"id":"2309.12259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-21T17:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"207c10af2abb1950618ab085520ca5a670d947d3d33d9904e5240786a44a8be0","abstract_canon_sha256":"5a8089346f2eefb10047a64a5d8349a76fe2bb3cb10d2bf95a7ac02055cd7ffb"},"schema_version":"1.0"},"canonical_sha256":"1f39a7fa992a0c3d647b52cbfffe4c996e0ce7ad7e343fd7d96371fb86c9d3c1","source":{"kind":"arxiv","id":"2309.12259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12259","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12259v1","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12259","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"D442P6UZFIGD","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"D442P6UZFIGD2ZD3","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"D442P6UZ","created_at":"2026-07-05T06:53:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:D442P6UZFIGD2ZD3KLF777SMTF","target":"record","payload":{"canonical_record":{"source":{"id":"2309.12259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-21T17:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"207c10af2abb1950618ab085520ca5a670d947d3d33d9904e5240786a44a8be0","abstract_canon_sha256":"5a8089346f2eefb10047a64a5d8349a76fe2bb3cb10d2bf95a7ac02055cd7ffb"},"schema_version":"1.0"},"canonical_sha256":"1f39a7fa992a0c3d647b52cbfffe4c996e0ce7ad7e343fd7d96371fb86c9d3c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:00.785747Z","signature_b64":"sq2tEUGrALeocTBxkx8197mr7r6ksISAOmGEFH7EuMjWKquobj2U0UHMV1KrgNXCnrI+d+fXC+V4qDvDQX6xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f39a7fa992a0c3d647b52cbfffe4c996e0ce7ad7e343fd7d96371fb86c9d3c1","last_reissued_at":"2026-07-05T06:53:00.785256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:00.785256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.12259","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":"2026-07-05T06:53:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jds7yvCMfzKnhIrj5yvQ6SzbO/28tyZ3ikWG5wErSsnjiKSOKWmhSzsukHkRFRIkIo28dT43nXgD9xGj4bE9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:43:20.475880Z"},"content_sha256":"f8fe80c11c2fb9c646b21d1a6cb4284f8a0b2adf341a0837fd6b26fcec5e3fc9","schema_version":"1.0","event_id":"sha256:f8fe80c11c2fb9c646b21d1a6cb4284f8a0b2adf341a0837fd6b26fcec5e3fc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:D442P6UZFIGD2ZD3KLF777SMTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Merging: A Flexible and Robust Soft Model Merging Approach for Enhanced Neural Network Performance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Liu, Hao Chen, Phuong Nguyen, Yelena Yesha, Yusen Wu","submitted_at":"2023-09-21T17:07:31Z","abstract_excerpt":"Stochastic Gradient Descent (SGD), a widely used optimization algorithm in deep learning, is often limited to converging to local optima due to the non-convex nature of the problem. Leveraging these local optima to improve model performance remains a challenging task. Given the inherent complexity of neural networks, the simple arithmetic averaging of the obtained local optima models in undesirable results. This paper proposes a {\\em soft merging} method that facilitates rapid merging of multiple models, simplifies the merging of specific parts of neural networks, and enhances robustness again"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12259","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/2309.12259/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":"2026-07-05T06:53:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JNBdXSp7Jaazr0aQx09gVBcH36Fqj0TJBB7198BSqghMnoKrZUarq4HMilv5RyzmE7C225TBunpqN3Neie69CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:43:20.476253Z"},"content_sha256":"4eb34b21dc5973ec1f14c3845b2c5bfbb9561b96cd98bc4521b54912dcca20e1","schema_version":"1.0","event_id":"sha256:4eb34b21dc5973ec1f14c3845b2c5bfbb9561b96cd98bc4521b54912dcca20e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D442P6UZFIGD2ZD3KLF777SMTF/bundle.json","state_url":"https://pith.science/pith/D442P6UZFIGD2ZD3KLF777SMTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D442P6UZFIGD2ZD3KLF777SMTF/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":"2026-07-07T14:43:20Z","links":{"resolver":"https://pith.science/pith/D442P6UZFIGD2ZD3KLF777SMTF","bundle":"https://pith.science/pith/D442P6UZFIGD2ZD3KLF777SMTF/bundle.json","state":"https://pith.science/pith/D442P6UZFIGD2ZD3KLF777SMTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D442P6UZFIGD2ZD3KLF777SMTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:D442P6UZFIGD2ZD3KLF777SMTF","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":"5a8089346f2eefb10047a64a5d8349a76fe2bb3cb10d2bf95a7ac02055cd7ffb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-21T17:07:31Z","title_canon_sha256":"207c10af2abb1950618ab085520ca5a670d947d3d33d9904e5240786a44a8be0"},"schema_version":"1.0","source":{"id":"2309.12259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12259","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12259v1","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12259","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"D442P6UZFIGD","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"D442P6UZFIGD2ZD3","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"D442P6UZ","created_at":"2026-07-05T06:53:00Z"}],"graph_snapshots":[{"event_id":"sha256:4eb34b21dc5973ec1f14c3845b2c5bfbb9561b96cd98bc4521b54912dcca20e1","target":"graph","created_at":"2026-07-05T06:53:00Z","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/2309.12259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic Gradient Descent (SGD), a widely used optimization algorithm in deep learning, is often limited to converging to local optima due to the non-convex nature of the problem. Leveraging these local optima to improve model performance remains a challenging task. Given the inherent complexity of neural networks, the simple arithmetic averaging of the obtained local optima models in undesirable results. This paper proposes a {\\em soft merging} method that facilitates rapid merging of multiple models, simplifies the merging of specific parts of neural networks, and enhances robustness again","authors_text":"Chao Liu, Hao Chen, Phuong Nguyen, Yelena Yesha, Yusen Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-21T17:07:31Z","title":"Soft Merging: A Flexible and Robust Soft Model Merging Approach for Enhanced Neural Network Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12259","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:f8fe80c11c2fb9c646b21d1a6cb4284f8a0b2adf341a0837fd6b26fcec5e3fc9","target":"record","created_at":"2026-07-05T06:53:00Z","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":"5a8089346f2eefb10047a64a5d8349a76fe2bb3cb10d2bf95a7ac02055cd7ffb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-21T17:07:31Z","title_canon_sha256":"207c10af2abb1950618ab085520ca5a670d947d3d33d9904e5240786a44a8be0"},"schema_version":"1.0","source":{"id":"2309.12259","kind":"arxiv","version":1}},"canonical_sha256":"1f39a7fa992a0c3d647b52cbfffe4c996e0ce7ad7e343fd7d96371fb86c9d3c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f39a7fa992a0c3d647b52cbfffe4c996e0ce7ad7e343fd7d96371fb86c9d3c1","first_computed_at":"2026-07-05T06:53:00.785256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:00.785256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sq2tEUGrALeocTBxkx8197mr7r6ksISAOmGEFH7EuMjWKquobj2U0UHMV1KrgNXCnrI+d+fXC+V4qDvDQX6xCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:00.785747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8fe80c11c2fb9c646b21d1a6cb4284f8a0b2adf341a0837fd6b26fcec5e3fc9","sha256:4eb34b21dc5973ec1f14c3845b2c5bfbb9561b96cd98bc4521b54912dcca20e1"],"state_sha256":"2faf781c47c327c861073bb2a2cb47087ea647247bdc702d6d84bd7c9b069a2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nqgXrtiUWxDKrpYDGAoFbB5kRGsQ1JruDYkJ0Rssac3d0rtH9kIOFDKUjKn4u6DjZ0Ks1N1QYseevCZD1hm3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:43:20.478103Z","bundle_sha256":"14c976ad75ab70706609e313c82452d894ed20e74bcc4f1c6d0fffeabd5c584d"}}