{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ETAADXDD275B57JOGTJ73IZGIN","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":"caf15206e5aeba6e99d32084f43d98379726d7a16c1535d5c28de6241b525025","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:40:31Z","title_canon_sha256":"a330a1805ccd12670ae0bb7df8617b12bc2dd0912a2d54652cd5aac9ff5e8984"},"schema_version":"1.0","source":{"id":"2310.05719","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05719","created_at":"2026-07-05T08:10:18Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05719v3","created_at":"2026-07-05T08:10:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05719","created_at":"2026-07-05T08:10:18Z"},{"alias_kind":"pith_short_12","alias_value":"ETAADXDD275B","created_at":"2026-07-05T08:10:18Z"},{"alias_kind":"pith_short_16","alias_value":"ETAADXDD275B57JO","created_at":"2026-07-05T08:10:18Z"},{"alias_kind":"pith_short_8","alias_value":"ETAADXDD","created_at":"2026-07-05T08:10:18Z"}],"graph_snapshots":[{"event_id":"sha256:9e3662d2b51e4d05e8f358e3b8925c0fe043e4691e6db6064289dea5fae31063","target":"graph","created_at":"2026-07-05T08:10:18Z","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/2310.05719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fusion is a technique for merging multiple independently-trained neural networks in order to combine their capabilities. Past attempts have been restricted to the case of fully-connected, convolutional, and residual networks. This paper presents a systematic approach for fusing two or more transformer-based networks exploiting Optimal Transport to (soft-)align the various architectural components. We flesh out an abstraction for layer alignment, that can generalize to arbitrary architectures - in principle - and we apply this to the key ingredients of Transformers such as multi-head self-atten","authors_text":"Jacopo Graldi, Marco Giordano, Moritz Imfeld, Sidak Pal Singh (ETH Zurich), Sotiris Anagnostidis, Thomas Hofmann","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:40:31Z","title":"Transformer Fusion with Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05719","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":"sha256:40b6765d27f95b0226a4430b78adee4b848bf1d69dcf6e8e1fbd41aede3539fd","target":"record","created_at":"2026-07-05T08:10:18Z","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":"caf15206e5aeba6e99d32084f43d98379726d7a16c1535d5c28de6241b525025","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:40:31Z","title_canon_sha256":"a330a1805ccd12670ae0bb7df8617b12bc2dd0912a2d54652cd5aac9ff5e8984"},"schema_version":"1.0","source":{"id":"2310.05719","kind":"arxiv","version":3}},"canonical_sha256":"24c001dc63d7fa1efd2e34d3fda326437d7a51cf0a1ee58018d258fe989cc7d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24c001dc63d7fa1efd2e34d3fda326437d7a51cf0a1ee58018d258fe989cc7d1","first_computed_at":"2026-07-05T08:10:18.649615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:18.649615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8NYlNAGw088ZD+KNeIZfTcb2PqUxQQ5ZTxqFcBXTdqxoPe52umljwqq8QrSNRDCT1e3j9pNtdaRTdI3hP1SBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:18.650105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05719","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40b6765d27f95b0226a4430b78adee4b848bf1d69dcf6e8e1fbd41aede3539fd","sha256:9e3662d2b51e4d05e8f358e3b8925c0fe043e4691e6db6064289dea5fae31063"],"state_sha256":"fd31f3ab9b626b101f5e7edfd61ce1c1a8580507cf9cf38b6a7890c11414788b"}