{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IJ533DCW6AZCEXMPCSK3M7TD6R","short_pith_number":"pith:IJ533DCW","canonical_record":{"source":{"id":"2504.09812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T02:21:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f25986ac68b55833d9f111ff21aab8180a76c9e7e5d0aeff145438c14bf5d1c8","abstract_canon_sha256":"bd90da58d4ccdcda992e1e66470983412e01f992397cf04c0bfc4a4a441858ce"},"schema_version":"1.0"},"canonical_sha256":"427bbd8c56f032225d8f1495b67e63f45c3825e4674a8abbd41ee69317c9d735","source":{"kind":"arxiv","id":"2504.09812","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09812","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09812v1","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09812","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"IJ533DCW6AZC","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"IJ533DCW6AZCEXMP","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"IJ533DCW","created_at":"2026-07-05T10:48:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IJ533DCW6AZCEXMPCSK3M7TD6R","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T02:21:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f25986ac68b55833d9f111ff21aab8180a76c9e7e5d0aeff145438c14bf5d1c8","abstract_canon_sha256":"bd90da58d4ccdcda992e1e66470983412e01f992397cf04c0bfc4a4a441858ce"},"schema_version":"1.0"},"canonical_sha256":"427bbd8c56f032225d8f1495b67e63f45c3825e4674a8abbd41ee69317c9d735","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:43.041300Z","signature_b64":"KDPMj4EVDANstM3E7094Hwsyy2zbIKnQ3CtelrdP1gkAIYVLq082AeckzuMpuGW6sdtNBOezqKQqE7M4rL2sDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"427bbd8c56f032225d8f1495b67e63f45c3825e4674a8abbd41ee69317c9d735","last_reissued_at":"2026-07-05T10:48:43.040853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:43.040853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09812","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":"2026-07-05T10:48:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iVyu8GjQTKqvwSTI558geAUI66TQPVrD1lUhpdUVoQ9B96tOja3Ey6XWKFzIQlnDQM1gH7mmH0bkn4FkOVgFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:18.787955Z"},"content_sha256":"21815ff280b393e2df44f45dae7ce3b0a79a3d738da58d81596868ccf9c8b543","schema_version":"1.0","event_id":"sha256:21815ff280b393e2df44f45dae7ce3b0a79a3d738da58d81596868ccf9c8b543"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IJ533DCW6AZCEXMPCSK3M7TD6R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Multi-Task Modeling through Automated Fusion of Trained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dayu Zhang, Jingxuan Zhou, Ji Wang, Weidong Bao, Zhengyi Zhong","submitted_at":"2025-04-14T02:21:45Z","abstract_excerpt":"Although multi-task learning is widely applied in intelligent services, traditional multi-task modeling methods often require customized designs based on specific task combinations, resulting in a cumbersome modeling process. Inspired by the rapid development and excellent performance of single-task models, this paper proposes an efficient multi-task modeling method that can automatically fuse trained single-task models with different structures and tasks to form a multi-task model. As a general framework, this method allows modelers to simply prepare trained models for the required tasks, sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09812","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/2504.09812/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":"2026-07-05T10:48:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HKDYJh3NbIdgr4MYJiCksWHI8yd7issMbgAWYZ+/juWWkJlsbTu/zu7u6JKYGq4fg7yF2XVAirIZAQnNHnA/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:18.788375Z"},"content_sha256":"4e68f19862c88c76d3431e60b14b33df1b016d81c2559660f87a03ca36452826","schema_version":"1.0","event_id":"sha256:4e68f19862c88c76d3431e60b14b33df1b016d81c2559660f87a03ca36452826"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJ533DCW6AZCEXMPCSK3M7TD6R/bundle.json","state_url":"https://pith.science/pith/IJ533DCW6AZCEXMPCSK3M7TD6R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJ533DCW6AZCEXMPCSK3M7TD6R/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":"2026-07-06T20:50:18Z","links":{"resolver":"https://pith.science/pith/IJ533DCW6AZCEXMPCSK3M7TD6R","bundle":"https://pith.science/pith/IJ533DCW6AZCEXMPCSK3M7TD6R/bundle.json","state":"https://pith.science/pith/IJ533DCW6AZCEXMPCSK3M7TD6R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJ533DCW6AZCEXMPCSK3M7TD6R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IJ533DCW6AZCEXMPCSK3M7TD6R","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":"bd90da58d4ccdcda992e1e66470983412e01f992397cf04c0bfc4a4a441858ce","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T02:21:45Z","title_canon_sha256":"f25986ac68b55833d9f111ff21aab8180a76c9e7e5d0aeff145438c14bf5d1c8"},"schema_version":"1.0","source":{"id":"2504.09812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09812","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09812v1","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09812","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"IJ533DCW6AZC","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"IJ533DCW6AZCEXMP","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"IJ533DCW","created_at":"2026-07-05T10:48:43Z"}],"graph_snapshots":[{"event_id":"sha256:4e68f19862c88c76d3431e60b14b33df1b016d81c2559660f87a03ca36452826","target":"graph","created_at":"2026-07-05T10:48:43Z","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/2504.09812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although multi-task learning is widely applied in intelligent services, traditional multi-task modeling methods often require customized designs based on specific task combinations, resulting in a cumbersome modeling process. Inspired by the rapid development and excellent performance of single-task models, this paper proposes an efficient multi-task modeling method that can automatically fuse trained single-task models with different structures and tasks to form a multi-task model. As a general framework, this method allows modelers to simply prepare trained models for the required tasks, sim","authors_text":"Dayu Zhang, Jingxuan Zhou, Ji Wang, Weidong Bao, Zhengyi Zhong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T02:21:45Z","title":"Efficient Multi-Task Modeling through Automated Fusion of Trained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09812","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":"sha256:21815ff280b393e2df44f45dae7ce3b0a79a3d738da58d81596868ccf9c8b543","target":"record","created_at":"2026-07-05T10:48:43Z","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":"bd90da58d4ccdcda992e1e66470983412e01f992397cf04c0bfc4a4a441858ce","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T02:21:45Z","title_canon_sha256":"f25986ac68b55833d9f111ff21aab8180a76c9e7e5d0aeff145438c14bf5d1c8"},"schema_version":"1.0","source":{"id":"2504.09812","kind":"arxiv","version":1}},"canonical_sha256":"427bbd8c56f032225d8f1495b67e63f45c3825e4674a8abbd41ee69317c9d735","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"427bbd8c56f032225d8f1495b67e63f45c3825e4674a8abbd41ee69317c9d735","first_computed_at":"2026-07-05T10:48:43.040853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:43.040853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KDPMj4EVDANstM3E7094Hwsyy2zbIKnQ3CtelrdP1gkAIYVLq082AeckzuMpuGW6sdtNBOezqKQqE7M4rL2sDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:43.041300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21815ff280b393e2df44f45dae7ce3b0a79a3d738da58d81596868ccf9c8b543","sha256:4e68f19862c88c76d3431e60b14b33df1b016d81c2559660f87a03ca36452826"],"state_sha256":"b3cb1873ee0161d06f5b319078cf04d1b54d7b5be6f5923e9a34128da530fb1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9JyCiTAGJZmmX2e8Ba2m0RncSmrouUXDkoqiZO6+f3piF62jpMv+7RXb8YEE3V4vNO6bEHK7ghPLX2PRGnlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:50:18.790400Z","bundle_sha256":"62e13cab1d0eb7ed35b9f991079aeab2f3d3c2c4f458b727fc50f28fe2d1abed"}}