{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EGXYD7IXLNQWBTI3PIKYTFMC7V","short_pith_number":"pith:EGXYD7IX","canonical_record":{"source":{"id":"2306.17465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T08:19:38Z","cross_cats_sorted":[],"title_canon_sha256":"8e1464b978242ec7187ad0064e62cd502c7d4d18e36042346576af720308d32c","abstract_canon_sha256":"be6d94dd924cfa67ff176437f81097898ab9491a5c768cdaab2682b4c1801e73"},"schema_version":"1.0"},"canonical_sha256":"21af81fd175b6160cd1b7a15899582fd5a12e720e2e40a5be8cf8899b7ba2df4","source":{"kind":"arxiv","id":"2306.17465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17465","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17465v1","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17465","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"EGXYD7IXLNQW","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"EGXYD7IXLNQWBTI3","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"EGXYD7IX","created_at":"2026-07-05T06:26:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EGXYD7IXLNQWBTI3PIKYTFMC7V","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T08:19:38Z","cross_cats_sorted":[],"title_canon_sha256":"8e1464b978242ec7187ad0064e62cd502c7d4d18e36042346576af720308d32c","abstract_canon_sha256":"be6d94dd924cfa67ff176437f81097898ab9491a5c768cdaab2682b4c1801e73"},"schema_version":"1.0"},"canonical_sha256":"21af81fd175b6160cd1b7a15899582fd5a12e720e2e40a5be8cf8899b7ba2df4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:27.510926Z","signature_b64":"U3dfRqC34I7ecz+/H4ib6LIwEW/gJEKoj119riqfTlxgguYviRycdJA3W8TpzR8yzRDB0zFDAeL+gblOuhHpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21af81fd175b6160cd1b7a15899582fd5a12e720e2e40a5be8cf8899b7ba2df4","last_reissued_at":"2026-07-05T06:26:27.510479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:27.510479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17465","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":"2026-07-05T06:26:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7HFS6Ft+Ra8a25nuBBcFRDc6uJ2v7li09qZORty+qseAaL5SlvkUrFqTHFWIMKZqkOWZfUTNltBT0A4ZDCsHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T19:54:40.937276Z"},"content_sha256":"821c7b39f6f02666f4ebc231088caf054d0274c471dffe512af2461308e4081f","schema_version":"1.0","event_id":"sha256:821c7b39f6f02666f4ebc231088caf054d0274c471dffe512af2461308e4081f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EGXYD7IXLNQWBTI3PIKYTFMC7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FedBone: Towards Large-Scale Federated Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenlong Gao, Qian Chen, Teng Zhang, Wuliang Huang, Xinlong Jiang, Yiqiang Chen","submitted_at":"2023-06-30T08:19:38Z","abstract_excerpt":"Heterogeneous federated multi-task learning (HFMTL) is a federated learning technique that combines heterogeneous tasks of different clients to achieve more accurate, comprehensive predictions. In real-world applications, visual and natural language tasks typically require large-scale models to extract high-level abstract features. However, large-scale models cannot be directly applied to existing federated multi-task learning methods. Existing HFML methods also disregard the impact of gradient conflicts on multi-task optimization during the federated aggregation process. In this work, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17465","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/2306.17465/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":"2026-07-05T06:26:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQRe/J98hUdnJjYGDLjT4BWMOJxWSoTYPZ7bqVDtBjdB1pAk7mn6z6sbRT/IHOQziHbm0cZuP4Ya9Mqucz/qBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T19:54:40.937955Z"},"content_sha256":"aa9e194645e8d42567f43c7529d8dc4959226f73a0fd4565b6f83bea4ad366c5","schema_version":"1.0","event_id":"sha256:aa9e194645e8d42567f43c7529d8dc4959226f73a0fd4565b6f83bea4ad366c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EGXYD7IXLNQWBTI3PIKYTFMC7V/bundle.json","state_url":"https://pith.science/pith/EGXYD7IXLNQWBTI3PIKYTFMC7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EGXYD7IXLNQWBTI3PIKYTFMC7V/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":"2026-07-12T19:54:40Z","links":{"resolver":"https://pith.science/pith/EGXYD7IXLNQWBTI3PIKYTFMC7V","bundle":"https://pith.science/pith/EGXYD7IXLNQWBTI3PIKYTFMC7V/bundle.json","state":"https://pith.science/pith/EGXYD7IXLNQWBTI3PIKYTFMC7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EGXYD7IXLNQWBTI3PIKYTFMC7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EGXYD7IXLNQWBTI3PIKYTFMC7V","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":"be6d94dd924cfa67ff176437f81097898ab9491a5c768cdaab2682b4c1801e73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T08:19:38Z","title_canon_sha256":"8e1464b978242ec7187ad0064e62cd502c7d4d18e36042346576af720308d32c"},"schema_version":"1.0","source":{"id":"2306.17465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17465","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17465v1","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17465","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"EGXYD7IXLNQW","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"EGXYD7IXLNQWBTI3","created_at":"2026-07-05T06:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"EGXYD7IX","created_at":"2026-07-05T06:26:27Z"}],"graph_snapshots":[{"event_id":"sha256:aa9e194645e8d42567f43c7529d8dc4959226f73a0fd4565b6f83bea4ad366c5","target":"graph","created_at":"2026-07-05T06:26:27Z","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/2306.17465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heterogeneous federated multi-task learning (HFMTL) is a federated learning technique that combines heterogeneous tasks of different clients to achieve more accurate, comprehensive predictions. In real-world applications, visual and natural language tasks typically require large-scale models to extract high-level abstract features. However, large-scale models cannot be directly applied to existing federated multi-task learning methods. Existing HFML methods also disregard the impact of gradient conflicts on multi-task optimization during the federated aggregation process. In this work, we prop","authors_text":"Chenlong Gao, Qian Chen, Teng Zhang, Wuliang Huang, Xinlong Jiang, Yiqiang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T08:19:38Z","title":"FedBone: Towards Large-Scale Federated Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17465","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":"sha256:821c7b39f6f02666f4ebc231088caf054d0274c471dffe512af2461308e4081f","target":"record","created_at":"2026-07-05T06:26:27Z","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":"be6d94dd924cfa67ff176437f81097898ab9491a5c768cdaab2682b4c1801e73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T08:19:38Z","title_canon_sha256":"8e1464b978242ec7187ad0064e62cd502c7d4d18e36042346576af720308d32c"},"schema_version":"1.0","source":{"id":"2306.17465","kind":"arxiv","version":1}},"canonical_sha256":"21af81fd175b6160cd1b7a15899582fd5a12e720e2e40a5be8cf8899b7ba2df4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21af81fd175b6160cd1b7a15899582fd5a12e720e2e40a5be8cf8899b7ba2df4","first_computed_at":"2026-07-05T06:26:27.510479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:27.510479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U3dfRqC34I7ecz+/H4ib6LIwEW/gJEKoj119riqfTlxgguYviRycdJA3W8TpzR8yzRDB0zFDAeL+gblOuhHpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:27.510926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:821c7b39f6f02666f4ebc231088caf054d0274c471dffe512af2461308e4081f","sha256:aa9e194645e8d42567f43c7529d8dc4959226f73a0fd4565b6f83bea4ad366c5"],"state_sha256":"cf9b135d33914ec36b001cb0b82db5bcc4c65efb8da2828a4d798978c3b0021f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5sfNLv05EkHihqUnwEZSIlQV9CGxxFNXgTbyFucpxt5hfYwTTh+gSaZeYW8FS55NGxtAyM52SHUynLVTJuR6Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T19:54:40.942858Z","bundle_sha256":"103bff2f4d5661bc8488937821b86f11e7c2e9f9f37111fb43abea4d0aac9744"}}