{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SH245CANO3PDDKHXMQHQPPV72Y","short_pith_number":"pith:SH245CAN","canonical_record":{"source":{"id":"2402.15638","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T22:46:14Z","cross_cats_sorted":[],"title_canon_sha256":"3f1537422dddff1fcc9304a6ffeece5a31fabf7e046b629ab986da4294a9b8ce","abstract_canon_sha256":"c442eddec49c6e856ae1a5f1bf322f142caa0ab6e47861919260dcf570a2ac60"},"schema_version":"1.0"},"canonical_sha256":"91f5ce880d76de31a8f7640f07bebfd631a685a7bb4bf6e7e32b9d622a12a7a0","source":{"kind":"arxiv","id":"2402.15638","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15638","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15638v2","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15638","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_12","alias_value":"SH245CANO3PD","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_16","alias_value":"SH245CANO3PDDKHX","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_8","alias_value":"SH245CAN","created_at":"2026-07-05T08:38:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SH245CANO3PDDKHXMQHQPPV72Y","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15638","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T22:46:14Z","cross_cats_sorted":[],"title_canon_sha256":"3f1537422dddff1fcc9304a6ffeece5a31fabf7e046b629ab986da4294a9b8ce","abstract_canon_sha256":"c442eddec49c6e856ae1a5f1bf322f142caa0ab6e47861919260dcf570a2ac60"},"schema_version":"1.0"},"canonical_sha256":"91f5ce880d76de31a8f7640f07bebfd631a685a7bb4bf6e7e32b9d622a12a7a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:57.735812Z","signature_b64":"QvSREbkLE0fM0Amyr4af78tV0j9ycvyByAt8LdBtNm0PbUL4VA3bfupKkntP9J6xX5RYKd87eY1WG36nizxdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91f5ce880d76de31a8f7640f07bebfd631a685a7bb4bf6e7e32b9d622a12a7a0","last_reissued_at":"2026-07-05T08:38:57.735275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:57.735275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15638","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":"2026-07-05T08:38:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ejqzr3AiP6VYgRmIy/vmMXW6H59Mu4xf79ZKdaLmFWyYHRU0I328ALo4MTKdiMsS489lZV9GoIx/L7ac6DmKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T23:43:40.915572Z"},"content_sha256":"23d01a9fdc8c26b6cd04507d3ca1c6135f57755968adc0a8f1e2c306f6b088d9","schema_version":"1.0","event_id":"sha256:23d01a9fdc8c26b6cd04507d3ca1c6135f57755968adc0a8f1e2c306f6b088d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SH245CANO3PDDKHXMQHQPPV72Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fair Resource Allocation in Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hao Ban, Kaiyi Ji","submitted_at":"2024-02-23T22:46:14Z","abstract_excerpt":"By jointly learning multiple tasks, multi-task learning (MTL) can leverage the shared knowledge across tasks, resulting in improved data efficiency and generalization performance. However, a major challenge in MTL lies in the presence of conflicting gradients, which can hinder the fair optimization of some tasks and subsequently impede MTL's ability to achieve better overall performance. Inspired by fair resource allocation in communication networks, we formulate the optimization of MTL as a utility maximization problem, where the loss decreases across tasks are maximized under different fairn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15638","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/2402.15638/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":"2026-07-05T08:38:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FddQm7okyGdePB/kHoalTmIuNqapnIGoiPawPdHZUFpK89xIPcK1xz+1buzksP9NO3l0MNjiUx2ubtYJDwlQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T23:43:40.916117Z"},"content_sha256":"bee2b40e732ed86510fefe038bd92af9d14dafc74d0b3956f916c20466bcc375","schema_version":"1.0","event_id":"sha256:bee2b40e732ed86510fefe038bd92af9d14dafc74d0b3956f916c20466bcc375"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SH245CANO3PDDKHXMQHQPPV72Y/bundle.json","state_url":"https://pith.science/pith/SH245CANO3PDDKHXMQHQPPV72Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SH245CANO3PDDKHXMQHQPPV72Y/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":"2026-08-03T23:43:40Z","links":{"resolver":"https://pith.science/pith/SH245CANO3PDDKHXMQHQPPV72Y","bundle":"https://pith.science/pith/SH245CANO3PDDKHXMQHQPPV72Y/bundle.json","state":"https://pith.science/pith/SH245CANO3PDDKHXMQHQPPV72Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SH245CANO3PDDKHXMQHQPPV72Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SH245CANO3PDDKHXMQHQPPV72Y","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":"c442eddec49c6e856ae1a5f1bf322f142caa0ab6e47861919260dcf570a2ac60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T22:46:14Z","title_canon_sha256":"3f1537422dddff1fcc9304a6ffeece5a31fabf7e046b629ab986da4294a9b8ce"},"schema_version":"1.0","source":{"id":"2402.15638","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15638","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15638v2","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15638","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_12","alias_value":"SH245CANO3PD","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_16","alias_value":"SH245CANO3PDDKHX","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_8","alias_value":"SH245CAN","created_at":"2026-07-05T08:38:57Z"}],"graph_snapshots":[{"event_id":"sha256:bee2b40e732ed86510fefe038bd92af9d14dafc74d0b3956f916c20466bcc375","target":"graph","created_at":"2026-07-05T08:38:57Z","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/2402.15638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By jointly learning multiple tasks, multi-task learning (MTL) can leverage the shared knowledge across tasks, resulting in improved data efficiency and generalization performance. However, a major challenge in MTL lies in the presence of conflicting gradients, which can hinder the fair optimization of some tasks and subsequently impede MTL's ability to achieve better overall performance. Inspired by fair resource allocation in communication networks, we formulate the optimization of MTL as a utility maximization problem, where the loss decreases across tasks are maximized under different fairn","authors_text":"Hao Ban, Kaiyi Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T22:46:14Z","title":"Fair Resource Allocation in Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15638","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":"sha256:23d01a9fdc8c26b6cd04507d3ca1c6135f57755968adc0a8f1e2c306f6b088d9","target":"record","created_at":"2026-07-05T08:38:57Z","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":"c442eddec49c6e856ae1a5f1bf322f142caa0ab6e47861919260dcf570a2ac60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T22:46:14Z","title_canon_sha256":"3f1537422dddff1fcc9304a6ffeece5a31fabf7e046b629ab986da4294a9b8ce"},"schema_version":"1.0","source":{"id":"2402.15638","kind":"arxiv","version":2}},"canonical_sha256":"91f5ce880d76de31a8f7640f07bebfd631a685a7bb4bf6e7e32b9d622a12a7a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91f5ce880d76de31a8f7640f07bebfd631a685a7bb4bf6e7e32b9d622a12a7a0","first_computed_at":"2026-07-05T08:38:57.735275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:57.735275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QvSREbkLE0fM0Amyr4af78tV0j9ycvyByAt8LdBtNm0PbUL4VA3bfupKkntP9J6xX5RYKd87eY1WG36nizxdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:57.735812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15638","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23d01a9fdc8c26b6cd04507d3ca1c6135f57755968adc0a8f1e2c306f6b088d9","sha256:bee2b40e732ed86510fefe038bd92af9d14dafc74d0b3956f916c20466bcc375"],"state_sha256":"b0a75a49be02026a491c8173a564cc3f8c2c3df0904049f782c36a7c8ea532ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/D50Kl1K+hUxmAdiNiBKcOKcui0D/l9Caqs8F8igCV3It85EGZ6txljceVzYqZC7QhGp7tL0G3BcSS/Iu4j7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T23:43:40.919596Z","bundle_sha256":"9948f5217f86cc3731f77d03e4edc6d7085eae355869766750a4c08cfab77359"}}