{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7TXPRI6NAFNTCOYDUMAXXN5FJR","short_pith_number":"pith:7TXPRI6N","canonical_record":{"source":{"id":"2405.17461","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:25:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ce1d9d89c8db532a083ecc6a25f1412c4478818899022b3c5c44d47dd5db6a0c","abstract_canon_sha256":"5cb8a71da9e29e69f7ee97444d5b1a785c8d7236c109f0bc59476bd7c4eac038"},"schema_version":"1.0"},"canonical_sha256":"fceef8a3cd015b313b03a3017bb7a54c4dee75ae11328f548dcb546cecd7ff23","source":{"kind":"arxiv","id":"2405.17461","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17461","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17461v2","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17461","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"7TXPRI6NAFNT","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"7TXPRI6NAFNTCOYD","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"7TXPRI6N","created_at":"2026-07-05T09:12:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7TXPRI6NAFNTCOYDUMAXXN5FJR","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17461","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:25:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ce1d9d89c8db532a083ecc6a25f1412c4478818899022b3c5c44d47dd5db6a0c","abstract_canon_sha256":"5cb8a71da9e29e69f7ee97444d5b1a785c8d7236c109f0bc59476bd7c4eac038"},"schema_version":"1.0"},"canonical_sha256":"fceef8a3cd015b313b03a3017bb7a54c4dee75ae11328f548dcb546cecd7ff23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:28.566916Z","signature_b64":"HpniwQLFmfRg9hmKdCWWznKe0pgA+HHGoVtceGgt0IVVa8cWT8zK2fqQYkYo4lIaYb8PiM0EIQ4O8EjKHWUxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fceef8a3cd015b313b03a3017bb7a54c4dee75ae11328f548dcb546cecd7ff23","last_reissued_at":"2026-07-05T09:12:28.566416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:28.566416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17461","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":"2026-07-05T09:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FWsyFwHb8AXVCgjjsOt0agXdcMfR4ymFUxR46EwG8yKj5aorqAyD98GEBkmVrM/56c01SJeMWQvKAuv9mbNaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:53:17.640914Z"},"content_sha256":"1a51e1cd3f8eef1b155af1efc8af42148bad7e823aee508f7fafad4d2e7a72c7","schema_version":"1.0","event_id":"sha256:1a51e1cd3f8eef1b155af1efc8af42148bad7e823aee508f7fafad4d2e7a72c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7TXPRI6NAFNTCOYDUMAXXN5FJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EMR-Merging: Tuning-Free High-Performance Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chenyu Huang, Peng Ye, Tao Chen, Tong He, Wanli Ouyang, Xiangyu Yue","submitted_at":"2024-05-23T05:25:45Z","abstract_excerpt":"The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention for its practicability. Existing model merging methods usually suffer from (1) significant performance degradation or (2) requiring tuning by additional data or training. In this paper, we rethink and analyze the existing model merging paradigm. We discover that using a single model's weights can hardly simulate all the models' performance. To tackle this issu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17461","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/2405.17461/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":"2026-07-05T09:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GXUcVMSS2FfK2tGKPWwBXCYtjt3G6r6HAZbbj+xRuW3DSwimP6k925g1xVWWkJQnuUE8XBeyJjkXST5fiECPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:53:17.641787Z"},"content_sha256":"57d8471004c0d56617bb3c9b69d1997594b9fb9a78692e127657e37875912a69","schema_version":"1.0","event_id":"sha256:57d8471004c0d56617bb3c9b69d1997594b9fb9a78692e127657e37875912a69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7TXPRI6NAFNTCOYDUMAXXN5FJR/bundle.json","state_url":"https://pith.science/pith/7TXPRI6NAFNTCOYDUMAXXN5FJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7TXPRI6NAFNTCOYDUMAXXN5FJR/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":"2026-08-06T09:53:17Z","links":{"resolver":"https://pith.science/pith/7TXPRI6NAFNTCOYDUMAXXN5FJR","bundle":"https://pith.science/pith/7TXPRI6NAFNTCOYDUMAXXN5FJR/bundle.json","state":"https://pith.science/pith/7TXPRI6NAFNTCOYDUMAXXN5FJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7TXPRI6NAFNTCOYDUMAXXN5FJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7TXPRI6NAFNTCOYDUMAXXN5FJR","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":"5cb8a71da9e29e69f7ee97444d5b1a785c8d7236c109f0bc59476bd7c4eac038","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:25:45Z","title_canon_sha256":"ce1d9d89c8db532a083ecc6a25f1412c4478818899022b3c5c44d47dd5db6a0c"},"schema_version":"1.0","source":{"id":"2405.17461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17461","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17461v2","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17461","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"7TXPRI6NAFNT","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"7TXPRI6NAFNTCOYD","created_at":"2026-07-05T09:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"7TXPRI6N","created_at":"2026-07-05T09:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:57d8471004c0d56617bb3c9b69d1997594b9fb9a78692e127657e37875912a69","target":"graph","created_at":"2026-07-05T09:12:28Z","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/2405.17461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention for its practicability. Existing model merging methods usually suffer from (1) significant performance degradation or (2) requiring tuning by additional data or training. In this paper, we rethink and analyze the existing model merging paradigm. We discover that using a single model's weights can hardly simulate all the models' performance. To tackle this issu","authors_text":"Chenyu Huang, Peng Ye, Tao Chen, Tong He, Wanli Ouyang, Xiangyu Yue","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:25:45Z","title":"EMR-Merging: Tuning-Free High-Performance Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17461","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":"sha256:1a51e1cd3f8eef1b155af1efc8af42148bad7e823aee508f7fafad4d2e7a72c7","target":"record","created_at":"2026-07-05T09:12:28Z","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":"5cb8a71da9e29e69f7ee97444d5b1a785c8d7236c109f0bc59476bd7c4eac038","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T05:25:45Z","title_canon_sha256":"ce1d9d89c8db532a083ecc6a25f1412c4478818899022b3c5c44d47dd5db6a0c"},"schema_version":"1.0","source":{"id":"2405.17461","kind":"arxiv","version":2}},"canonical_sha256":"fceef8a3cd015b313b03a3017bb7a54c4dee75ae11328f548dcb546cecd7ff23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fceef8a3cd015b313b03a3017bb7a54c4dee75ae11328f548dcb546cecd7ff23","first_computed_at":"2026-07-05T09:12:28.566416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:28.566416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HpniwQLFmfRg9hmKdCWWznKe0pgA+HHGoVtceGgt0IVVa8cWT8zK2fqQYkYo4lIaYb8PiM0EIQ4O8EjKHWUxAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:28.566916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a51e1cd3f8eef1b155af1efc8af42148bad7e823aee508f7fafad4d2e7a72c7","sha256:57d8471004c0d56617bb3c9b69d1997594b9fb9a78692e127657e37875912a69"],"state_sha256":"01981d54661aabd5ad13de81895bf65249acdba432d69bdb40257c1bb78f2298"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/5lBC/VuKkjPG4IJqKC9Jh4mubO7VAtnA3uUSZytStdxTViEdwekLrY1QjlsauDk6PMkZFKw/iwnE9l+h0CBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:53:17.647479Z","bundle_sha256":"4d90e2ba4755fada971cf05f8839aa29a59f35e29e4461b6ae715c35650fb43d"}}