{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NMNW5IJ5MMS37O7W5MOIOJ72BG","short_pith_number":"pith:NMNW5IJ5","canonical_record":{"source":{"id":"2409.18893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-27T16:31:31Z","cross_cats_sorted":[],"title_canon_sha256":"18e94590be427c068964a7bd98b718b2d1f5e8e38d0e8577295cb979979392f3","abstract_canon_sha256":"d274b154bda9ec14fe605a2e52a3ee43b5727ce821ca2ceef2ebec21ffebb8e8"},"schema_version":"1.0"},"canonical_sha256":"6b1b6ea13d6325bfbbf6eb1c8727fa09ba889db486b78d476a07baf0001c8648","source":{"kind":"arxiv","id":"2409.18893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18893","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18893v1","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18893","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"NMNW5IJ5MMS3","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"NMNW5IJ5MMS37O7W","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"NMNW5IJ5","created_at":"2026-07-05T09:12:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NMNW5IJ5MMS37O7W5MOIOJ72BG","target":"record","payload":{"canonical_record":{"source":{"id":"2409.18893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-27T16:31:31Z","cross_cats_sorted":[],"title_canon_sha256":"18e94590be427c068964a7bd98b718b2d1f5e8e38d0e8577295cb979979392f3","abstract_canon_sha256":"d274b154bda9ec14fe605a2e52a3ee43b5727ce821ca2ceef2ebec21ffebb8e8"},"schema_version":"1.0"},"canonical_sha256":"6b1b6ea13d6325bfbbf6eb1c8727fa09ba889db486b78d476a07baf0001c8648","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:49.718638Z","signature_b64":"RToHXQmhNJ3LNoGCSAZ9anT0/UuLiDPcIXKm5kYz7Xu3GePPBfDtLpbOntWALVkNpSWK/eJJwqufIz/H/7s3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b1b6ea13d6325bfbbf6eb1c8727fa09ba889db486b78d476a07baf0001c8648","last_reissued_at":"2026-07-05T09:12:49.718212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:49.718212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.18893","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":"2026-07-05T09:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8SrBq8F2EcF2g/rXu5CNaBbx2u6HSAuw2uOroELf+aZw91wkhn4Ts103SEommYNGuO6jmx9fArOxyidu0lu+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:21:12.004732Z"},"content_sha256":"21b96b0ee2687ab2753f5b295a2aeb400e94f05efcc3215ba15669c35a13c9b8","schema_version":"1.0","event_id":"sha256:21b96b0ee2687ab2753f5b295a2aeb400e94f05efcc3215ba15669c35a13c9b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NMNW5IJ5MMS37O7W5MOIOJ72BG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jibin Wu, Kay Chen Tan, Liang Feng, Xingyu Wu, Yu Zhou","submitted_at":"2024-09-27T16:31:31Z","abstract_excerpt":"Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to bypass the need for original training data and further training processes. However, most existing model merging approaches focus solely on exploring the parameter space, merging models with identical architectures. Merging within the architecture space, despite its potential, remains in its early stages due to the vast search space and the challenges of layer "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18893","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/2409.18893/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":"2026-07-05T09:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOhH9wXAbEUH2IBovfwIlo3noT7QFO0V5lAI4gero1A7BJ43AXvQAh6FYGG8PmSKIYdmnPD8H4u/8/PvJ8+RAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:21:12.005301Z"},"content_sha256":"549e5e5ad4eaffd637f316a3a46da0a981572d6212cf3538bbd0ed987e599da5","schema_version":"1.0","event_id":"sha256:549e5e5ad4eaffd637f316a3a46da0a981572d6212cf3538bbd0ed987e599da5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMNW5IJ5MMS37O7W5MOIOJ72BG/bundle.json","state_url":"https://pith.science/pith/NMNW5IJ5MMS37O7W5MOIOJ72BG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMNW5IJ5MMS37O7W5MOIOJ72BG/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":"2026-08-22T09:21:12Z","links":{"resolver":"https://pith.science/pith/NMNW5IJ5MMS37O7W5MOIOJ72BG","bundle":"https://pith.science/pith/NMNW5IJ5MMS37O7W5MOIOJ72BG/bundle.json","state":"https://pith.science/pith/NMNW5IJ5MMS37O7W5MOIOJ72BG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMNW5IJ5MMS37O7W5MOIOJ72BG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NMNW5IJ5MMS37O7W5MOIOJ72BG","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":"d274b154bda9ec14fe605a2e52a3ee43b5727ce821ca2ceef2ebec21ffebb8e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-27T16:31:31Z","title_canon_sha256":"18e94590be427c068964a7bd98b718b2d1f5e8e38d0e8577295cb979979392f3"},"schema_version":"1.0","source":{"id":"2409.18893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18893","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18893v1","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18893","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"NMNW5IJ5MMS3","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"NMNW5IJ5MMS37O7W","created_at":"2026-07-05T09:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"NMNW5IJ5","created_at":"2026-07-05T09:12:49Z"}],"graph_snapshots":[{"event_id":"sha256:549e5e5ad4eaffd637f316a3a46da0a981572d6212cf3538bbd0ed987e599da5","target":"graph","created_at":"2026-07-05T09:12:49Z","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/2409.18893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to bypass the need for original training data and further training processes. However, most existing model merging approaches focus solely on exploring the parameter space, merging models with identical architectures. Merging within the architecture space, despite its potential, remains in its early stages due to the vast search space and the challenges of layer ","authors_text":"Jibin Wu, Kay Chen Tan, Liang Feng, Xingyu Wu, Yu Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-27T16:31:31Z","title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18893","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":"sha256:21b96b0ee2687ab2753f5b295a2aeb400e94f05efcc3215ba15669c35a13c9b8","target":"record","created_at":"2026-07-05T09:12:49Z","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":"d274b154bda9ec14fe605a2e52a3ee43b5727ce821ca2ceef2ebec21ffebb8e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-27T16:31:31Z","title_canon_sha256":"18e94590be427c068964a7bd98b718b2d1f5e8e38d0e8577295cb979979392f3"},"schema_version":"1.0","source":{"id":"2409.18893","kind":"arxiv","version":1}},"canonical_sha256":"6b1b6ea13d6325bfbbf6eb1c8727fa09ba889db486b78d476a07baf0001c8648","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b1b6ea13d6325bfbbf6eb1c8727fa09ba889db486b78d476a07baf0001c8648","first_computed_at":"2026-07-05T09:12:49.718212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:49.718212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RToHXQmhNJ3LNoGCSAZ9anT0/UuLiDPcIXKm5kYz7Xu3GePPBfDtLpbOntWALVkNpSWK/eJJwqufIz/H/7s3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:49.718638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21b96b0ee2687ab2753f5b295a2aeb400e94f05efcc3215ba15669c35a13c9b8","sha256:549e5e5ad4eaffd637f316a3a46da0a981572d6212cf3538bbd0ed987e599da5"],"state_sha256":"57833026127a978c285006b14f7a7f729ff6097dd312fa79ae23a520956d4b54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9UTD4oQtz0Mf56fxN744XIzg53UENL17j8U9cxPONee69yuhxqEsT0s9OmaEnRifINHue81BQYp9yd83N4eBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:21:12.011223Z","bundle_sha256":"da28c24724c81db0e4b7a3b13e154b1f2a260b23cf30b76b10ef06cc4d319607"}}