{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VBCF4BVSFFLDS5EO5S7LAWBVKV","short_pith_number":"pith:VBCF4BVS","canonical_record":{"source":{"id":"2307.06966","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T09:39:10Z","cross_cats_sorted":[],"title_canon_sha256":"e166101f4146c8183bcfa8234d17bf929b3299fbdba2ed7989f5ef61e2705dbd","abstract_canon_sha256":"7319674546d04f34ac2e2630e9aa9977b572568ac85aec6e37fea8011882734b"},"schema_version":"1.0"},"canonical_sha256":"a8445e06b2295639748eecbeb05835556f5bb0477f9d0fbb38010710d33daf66","source":{"kind":"arxiv","id":"2307.06966","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06966","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06966v3","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06966","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"VBCF4BVSFFLD","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"VBCF4BVSFFLDS5EO","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"VBCF4BVS","created_at":"2026-07-05T07:57:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VBCF4BVSFFLDS5EO5S7LAWBVKV","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06966","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T09:39:10Z","cross_cats_sorted":[],"title_canon_sha256":"e166101f4146c8183bcfa8234d17bf929b3299fbdba2ed7989f5ef61e2705dbd","abstract_canon_sha256":"7319674546d04f34ac2e2630e9aa9977b572568ac85aec6e37fea8011882734b"},"schema_version":"1.0"},"canonical_sha256":"a8445e06b2295639748eecbeb05835556f5bb0477f9d0fbb38010710d33daf66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:42.010175Z","signature_b64":"wCxndrTGIUISLmSkDdw30PvYfBtfwi1cyDlFycL9RSvtlqQuxafJG3bwxcUE8VV3YeSpZK5bkmVRH9oiinjgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8445e06b2295639748eecbeb05835556f5bb0477f9d0fbb38010710d33daf66","last_reissued_at":"2026-07-05T07:57:42.009670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:42.009670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06966","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":"2026-07-05T07:57:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duVqMPDPQETpWFHwd77jyBys3ZsXcMUfjh42jCR4UsnPbQtsARcrYUUsxt2YuHCaPIUS6zKXkHu2oHY6WPleCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:10:31.356572Z"},"content_sha256":"24f1e2c96f3bfb2bc6247ca2036bb60ef3e9ca6fb64d93f25659dbc40ba39aa3","schema_version":"1.0","event_id":"sha256:24f1e2c96f3bfb2bc6247ca2036bb60ef3e9ca6fb64d93f25659dbc40ba39aa3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VBCF4BVSFFLDS5EO5S7LAWBVKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Layer-wise Linear Mode Connectivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Asja Fischer, Linara Adilova, Maksym Andriushchenko, Martin Jaggi, Michael Kamp","submitted_at":"2023-07-13T09:39:10Z","abstract_excerpt":"Averaging neural network parameters is an intuitive method for fusing the knowledge of two independent models. It is most prominently used in federated learning. If models are averaged at the end of training, this can only lead to a good performing model if the loss surface of interest is very particular, i.e., the loss in the midpoint between the two models needs to be sufficiently low. This is impossible to guarantee for the non-convex losses of state-of-the-art networks. For averaging models trained on vastly different datasets, it was proposed to average only the parameters of particular l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06966","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/2307.06966/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":"2026-07-05T07:57:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jl0ndUbnqyHzmHpqSIKW86wKqSSaTCBIFCez6t4yekKWqqVERKm+vfihAE6lT2jKSBRnJgnDxTQyqlIIvSUADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:10:31.356951Z"},"content_sha256":"4bd12007c7aba6b8b9594dd314a3beeae9d52de1bdecb44017454a9ce78fa8ca","schema_version":"1.0","event_id":"sha256:4bd12007c7aba6b8b9594dd314a3beeae9d52de1bdecb44017454a9ce78fa8ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBCF4BVSFFLDS5EO5S7LAWBVKV/bundle.json","state_url":"https://pith.science/pith/VBCF4BVSFFLDS5EO5S7LAWBVKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBCF4BVSFFLDS5EO5S7LAWBVKV/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":"2026-07-06T19:10:31Z","links":{"resolver":"https://pith.science/pith/VBCF4BVSFFLDS5EO5S7LAWBVKV","bundle":"https://pith.science/pith/VBCF4BVSFFLDS5EO5S7LAWBVKV/bundle.json","state":"https://pith.science/pith/VBCF4BVSFFLDS5EO5S7LAWBVKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBCF4BVSFFLDS5EO5S7LAWBVKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VBCF4BVSFFLDS5EO5S7LAWBVKV","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":"7319674546d04f34ac2e2630e9aa9977b572568ac85aec6e37fea8011882734b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T09:39:10Z","title_canon_sha256":"e166101f4146c8183bcfa8234d17bf929b3299fbdba2ed7989f5ef61e2705dbd"},"schema_version":"1.0","source":{"id":"2307.06966","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06966","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06966v3","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06966","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"VBCF4BVSFFLD","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"VBCF4BVSFFLDS5EO","created_at":"2026-07-05T07:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"VBCF4BVS","created_at":"2026-07-05T07:57:42Z"}],"graph_snapshots":[{"event_id":"sha256:4bd12007c7aba6b8b9594dd314a3beeae9d52de1bdecb44017454a9ce78fa8ca","target":"graph","created_at":"2026-07-05T07:57:42Z","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/2307.06966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Averaging neural network parameters is an intuitive method for fusing the knowledge of two independent models. It is most prominently used in federated learning. If models are averaged at the end of training, this can only lead to a good performing model if the loss surface of interest is very particular, i.e., the loss in the midpoint between the two models needs to be sufficiently low. This is impossible to guarantee for the non-convex losses of state-of-the-art networks. For averaging models trained on vastly different datasets, it was proposed to average only the parameters of particular l","authors_text":"Asja Fischer, Linara Adilova, Maksym Andriushchenko, Martin Jaggi, Michael Kamp","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T09:39:10Z","title":"Layer-wise Linear Mode Connectivity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06966","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":"sha256:24f1e2c96f3bfb2bc6247ca2036bb60ef3e9ca6fb64d93f25659dbc40ba39aa3","target":"record","created_at":"2026-07-05T07:57:42Z","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":"7319674546d04f34ac2e2630e9aa9977b572568ac85aec6e37fea8011882734b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T09:39:10Z","title_canon_sha256":"e166101f4146c8183bcfa8234d17bf929b3299fbdba2ed7989f5ef61e2705dbd"},"schema_version":"1.0","source":{"id":"2307.06966","kind":"arxiv","version":3}},"canonical_sha256":"a8445e06b2295639748eecbeb05835556f5bb0477f9d0fbb38010710d33daf66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8445e06b2295639748eecbeb05835556f5bb0477f9d0fbb38010710d33daf66","first_computed_at":"2026-07-05T07:57:42.009670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:42.009670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wCxndrTGIUISLmSkDdw30PvYfBtfwi1cyDlFycL9RSvtlqQuxafJG3bwxcUE8VV3YeSpZK5bkmVRH9oiinjgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:42.010175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06966","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24f1e2c96f3bfb2bc6247ca2036bb60ef3e9ca6fb64d93f25659dbc40ba39aa3","sha256:4bd12007c7aba6b8b9594dd314a3beeae9d52de1bdecb44017454a9ce78fa8ca"],"state_sha256":"39f8fe7218aab5a16e68976dfd404bbdca641c158faa518a5d3b9bf8b3730897"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x11NuLTQwEs+VcVfiLpPoW4XdKWNbcS7LFz6UCjpwqNoKgFDjH9JX91ecmUx2gKG4eh2Va0YN7L99a1nIuoRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:10:31.358867Z","bundle_sha256":"b3b701823c084e19849dc05361d022b1450db96a847e928dd7c7c4446d0e24fe"}}