{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YQ2P4H6C5WIYOBEJMW2KRQ3DF3","short_pith_number":"pith:YQ2P4H6C","canonical_record":{"source":{"id":"2403.00986","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T21:16:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3316dea5b6cb2c4bfad438b6d6534398aef3e696d5d5d772240933e58708aee1","abstract_canon_sha256":"fd30307ae36cab6f7d918f29ac553c4a4461e73862d413c063b16ff29d7661b3"},"schema_version":"1.0"},"canonical_sha256":"c434fe1fc2ed9187048965b4a8c3632ed6628516f7faa00ac8a1e60f3c606a0d","source":{"kind":"arxiv","id":"2403.00986","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00986","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00986v3","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00986","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQ2P4H6C5WIY","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"YQ2P4H6C5WIYOBEJ","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"YQ2P4H6C","created_at":"2026-07-05T09:49:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YQ2P4H6C5WIYOBEJMW2KRQ3DF3","target":"record","payload":{"canonical_record":{"source":{"id":"2403.00986","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T21:16:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3316dea5b6cb2c4bfad438b6d6534398aef3e696d5d5d772240933e58708aee1","abstract_canon_sha256":"fd30307ae36cab6f7d918f29ac553c4a4461e73862d413c063b16ff29d7661b3"},"schema_version":"1.0"},"canonical_sha256":"c434fe1fc2ed9187048965b4a8c3632ed6628516f7faa00ac8a1e60f3c606a0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:41.354503Z","signature_b64":"N1e5Bwm74hL3OGGtwZdGdz45NJIHqwzo3J9/Z2FowgSQ7mAg50jK8mrsbINpkffPo51ICl65RzPCLBAbCU4qDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c434fe1fc2ed9187048965b4a8c3632ed6628516f7faa00ac8a1e60f3c606a0d","last_reissued_at":"2026-07-05T09:49:41.354039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:41.354039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.00986","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":"2026-07-05T09:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXWYviBoeBL8ZRbXU3nsgT+pvHvFUufSeBLvXqM7bOuGlXvbDVccsNKsaPBXK1SlQonG6VCFScb6RJx4mAVEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:40:42.158856Z"},"content_sha256":"a41b988c0441bd8d12c5101191b22c9588627a033146c5e5280ab90e7dfa774b","schema_version":"1.0","event_id":"sha256:a41b988c0441bd8d12c5101191b22c9588627a033146c5e5280ab90e7dfa774b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YQ2P4H6C5WIYOBEJMW2KRQ3DF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Merging Text Transformer Models from Different Initializations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Maha Elbayad, Neha Verma","submitted_at":"2024-03-01T21:16:29Z","abstract_excerpt":"Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer architecture, despite its dominant popularity in the language domain. Therefore, in this work, we investigate the extent to which separate Transformer minima learn similar features, and propose a model merging technique to investigate the relationship between these minima in the loss landscape. The specifics of the architecture, like its residual connections, multi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00986","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/2403.00986/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":"2026-07-05T09:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nLsJunKd2+YZdfwVxsaVRssbDbnXG8huJkc94T2xw8r/aZGHwr98EVGph6ltKfLnpPlwQ4i5mVc6yBGtSfPxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:40:42.159477Z"},"content_sha256":"8c5f6d04acb82d29d821c521e1ae02434d9d4c8c0de39013eefaa2ec284c3d5f","schema_version":"1.0","event_id":"sha256:8c5f6d04acb82d29d821c521e1ae02434d9d4c8c0de39013eefaa2ec284c3d5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQ2P4H6C5WIYOBEJMW2KRQ3DF3/bundle.json","state_url":"https://pith.science/pith/YQ2P4H6C5WIYOBEJMW2KRQ3DF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQ2P4H6C5WIYOBEJMW2KRQ3DF3/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":"2026-07-05T14:40:42Z","links":{"resolver":"https://pith.science/pith/YQ2P4H6C5WIYOBEJMW2KRQ3DF3","bundle":"https://pith.science/pith/YQ2P4H6C5WIYOBEJMW2KRQ3DF3/bundle.json","state":"https://pith.science/pith/YQ2P4H6C5WIYOBEJMW2KRQ3DF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQ2P4H6C5WIYOBEJMW2KRQ3DF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YQ2P4H6C5WIYOBEJMW2KRQ3DF3","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":"fd30307ae36cab6f7d918f29ac553c4a4461e73862d413c063b16ff29d7661b3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T21:16:29Z","title_canon_sha256":"3316dea5b6cb2c4bfad438b6d6534398aef3e696d5d5d772240933e58708aee1"},"schema_version":"1.0","source":{"id":"2403.00986","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00986","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00986v3","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00986","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQ2P4H6C5WIY","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"YQ2P4H6C5WIYOBEJ","created_at":"2026-07-05T09:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"YQ2P4H6C","created_at":"2026-07-05T09:49:41Z"}],"graph_snapshots":[{"event_id":"sha256:8c5f6d04acb82d29d821c521e1ae02434d9d4c8c0de39013eefaa2ec284c3d5f","target":"graph","created_at":"2026-07-05T09:49:41Z","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/2403.00986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer architecture, despite its dominant popularity in the language domain. Therefore, in this work, we investigate the extent to which separate Transformer minima learn similar features, and propose a model merging technique to investigate the relationship between these minima in the loss landscape. The specifics of the architecture, like its residual connections, multi-","authors_text":"Maha Elbayad, Neha Verma","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T21:16:29Z","title":"Merging Text Transformer Models from Different Initializations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00986","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:a41b988c0441bd8d12c5101191b22c9588627a033146c5e5280ab90e7dfa774b","target":"record","created_at":"2026-07-05T09:49:41Z","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":"fd30307ae36cab6f7d918f29ac553c4a4461e73862d413c063b16ff29d7661b3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T21:16:29Z","title_canon_sha256":"3316dea5b6cb2c4bfad438b6d6534398aef3e696d5d5d772240933e58708aee1"},"schema_version":"1.0","source":{"id":"2403.00986","kind":"arxiv","version":3}},"canonical_sha256":"c434fe1fc2ed9187048965b4a8c3632ed6628516f7faa00ac8a1e60f3c606a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c434fe1fc2ed9187048965b4a8c3632ed6628516f7faa00ac8a1e60f3c606a0d","first_computed_at":"2026-07-05T09:49:41.354039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:41.354039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N1e5Bwm74hL3OGGtwZdGdz45NJIHqwzo3J9/Z2FowgSQ7mAg50jK8mrsbINpkffPo51ICl65RzPCLBAbCU4qDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:41.354503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00986","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a41b988c0441bd8d12c5101191b22c9588627a033146c5e5280ab90e7dfa774b","sha256:8c5f6d04acb82d29d821c521e1ae02434d9d4c8c0de39013eefaa2ec284c3d5f"],"state_sha256":"7a2d9bfdd2d31e23d20b16896bc30e1917e3628b150732bd6206b421af1d32c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aUx45sZd5OwqUume4SCGyUGBl5ERz3592H8/0sRCJ0/xuWhWvzqAnHz24nm9yyQ3ZA+y2b04NsyQcfhDUVjnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:40:42.162393Z","bundle_sha256":"285f5dc02e17a75df9507cb726f8f87bd4b64324820253b938119c4c9960eaaf"}}