{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NB3G7NLCQEENVEU2IXELOVWSNW","short_pith_number":"pith:NB3G7NLC","canonical_record":{"source":{"id":"2111.10603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-20T14:28:32Z","cross_cats_sorted":[],"title_canon_sha256":"d84f8826e37729f33fd3a0a7736fbb962691ce6ba581abe0efb3aefe39e75613","abstract_canon_sha256":"e042dfca00a9ac0051390bfbc204eb2cdc523ee194301db437b382c04464ae61"},"schema_version":"1.0"},"canonical_sha256":"68766fb5628108da929a45c8b756d26d9d7877c9a4cea3111cef6f16e487f99e","source":{"kind":"arxiv","id":"2111.10603","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10603","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10603v2","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10603","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"NB3G7NLCQEEN","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"NB3G7NLCQEENVEU2","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"NB3G7NLC","created_at":"2026-07-05T04:43:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NB3G7NLCQEENVEU2IXELOVWSNW","target":"record","payload":{"canonical_record":{"source":{"id":"2111.10603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-20T14:28:32Z","cross_cats_sorted":[],"title_canon_sha256":"d84f8826e37729f33fd3a0a7736fbb962691ce6ba581abe0efb3aefe39e75613","abstract_canon_sha256":"e042dfca00a9ac0051390bfbc204eb2cdc523ee194301db437b382c04464ae61"},"schema_version":"1.0"},"canonical_sha256":"68766fb5628108da929a45c8b756d26d9d7877c9a4cea3111cef6f16e487f99e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:58.328090Z","signature_b64":"F/eOZoNJuj2BuEtpQvUd9sG/LBspDiLPlSb9aSgNT4bQo8jmdE9OEjwTpZ0Qkk62DCXRJXOXekTSQCk6AHu4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68766fb5628108da929a45c8b756d26d9d7877c9a4cea3111cef6f16e487f99e","last_reissued_at":"2026-07-05T04:43:58.327536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:58.327536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.10603","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":"2026-07-05T04:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sjW/9t/tq0m0+0dfSfnGa3XYjJNnoCV0r6OEV+gi5XSGAjlcOmwGRvKF4wIUmk3W93/z4GEPqFua1iPh+lLOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:34:06.175579Z"},"content_sha256":"4155057de6d513166bf225e814b194b8240734eec08925ed87fced8960d117dd","schema_version":"1.0","event_id":"sha256:4155057de6d513166bf225e814b194b8240734eec08925ed87fced8960d117dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NB3G7NLCQEENVEU2IXELOVWSNW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baijiong Lin, Feiyang Ye, Ivor W. Tsang, Yu Zhang","submitted_at":"2021-11-20T14:28:32Z","abstract_excerpt":"Multi-Task Learning (MTL) has achieved success in various fields. However, how to balance different tasks to achieve good performance is a key problem. To achieve the task balancing, there are many works to carefully design dynamical loss/gradient weighting strategies but the basic random experiments are ignored to examine their effectiveness. In this paper, we propose the Random Weighting (RW) methods, including Random Loss Weighting (RLW) and Random Gradient Weighting (RGW), where an MTL model is trained with random loss/gradient weights sampled from a distribution. To show the effectiveness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10603","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/2111.10603/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":"2026-07-05T04:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pOvXWT0EARABqoNG7pJ79xXGmnQLpmqN81bwl0BDRRUKL++40Apn0VBNa+cnWC5Z15+VdQ6nkc5kJuaQhbmmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:34:06.176070Z"},"content_sha256":"dd489b6fbab23f903a0cf77a4d077153a4e0ba5c63409b725cc4ee8788b3eb7f","schema_version":"1.0","event_id":"sha256:dd489b6fbab23f903a0cf77a4d077153a4e0ba5c63409b725cc4ee8788b3eb7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NB3G7NLCQEENVEU2IXELOVWSNW/bundle.json","state_url":"https://pith.science/pith/NB3G7NLCQEENVEU2IXELOVWSNW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NB3G7NLCQEENVEU2IXELOVWSNW/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":"2026-08-05T09:34:06Z","links":{"resolver":"https://pith.science/pith/NB3G7NLCQEENVEU2IXELOVWSNW","bundle":"https://pith.science/pith/NB3G7NLCQEENVEU2IXELOVWSNW/bundle.json","state":"https://pith.science/pith/NB3G7NLCQEENVEU2IXELOVWSNW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NB3G7NLCQEENVEU2IXELOVWSNW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NB3G7NLCQEENVEU2IXELOVWSNW","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":"e042dfca00a9ac0051390bfbc204eb2cdc523ee194301db437b382c04464ae61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-20T14:28:32Z","title_canon_sha256":"d84f8826e37729f33fd3a0a7736fbb962691ce6ba581abe0efb3aefe39e75613"},"schema_version":"1.0","source":{"id":"2111.10603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10603","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10603v2","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10603","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"NB3G7NLCQEEN","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"NB3G7NLCQEENVEU2","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"NB3G7NLC","created_at":"2026-07-05T04:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:dd489b6fbab23f903a0cf77a4d077153a4e0ba5c63409b725cc4ee8788b3eb7f","target":"graph","created_at":"2026-07-05T04:43:58Z","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/2111.10603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Task Learning (MTL) has achieved success in various fields. However, how to balance different tasks to achieve good performance is a key problem. To achieve the task balancing, there are many works to carefully design dynamical loss/gradient weighting strategies but the basic random experiments are ignored to examine their effectiveness. In this paper, we propose the Random Weighting (RW) methods, including Random Loss Weighting (RLW) and Random Gradient Weighting (RGW), where an MTL model is trained with random loss/gradient weights sampled from a distribution. To show the effectiveness","authors_text":"Baijiong Lin, Feiyang Ye, Ivor W. Tsang, Yu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-20T14:28:32Z","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10603","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":"sha256:4155057de6d513166bf225e814b194b8240734eec08925ed87fced8960d117dd","target":"record","created_at":"2026-07-05T04:43:58Z","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":"e042dfca00a9ac0051390bfbc204eb2cdc523ee194301db437b382c04464ae61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-20T14:28:32Z","title_canon_sha256":"d84f8826e37729f33fd3a0a7736fbb962691ce6ba581abe0efb3aefe39e75613"},"schema_version":"1.0","source":{"id":"2111.10603","kind":"arxiv","version":2}},"canonical_sha256":"68766fb5628108da929a45c8b756d26d9d7877c9a4cea3111cef6f16e487f99e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68766fb5628108da929a45c8b756d26d9d7877c9a4cea3111cef6f16e487f99e","first_computed_at":"2026-07-05T04:43:58.327536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:58.327536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F/eOZoNJuj2BuEtpQvUd9sG/LBspDiLPlSb9aSgNT4bQo8jmdE9OEjwTpZ0Qkk62DCXRJXOXekTSQCk6AHu4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:58.328090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.10603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4155057de6d513166bf225e814b194b8240734eec08925ed87fced8960d117dd","sha256:dd489b6fbab23f903a0cf77a4d077153a4e0ba5c63409b725cc4ee8788b3eb7f"],"state_sha256":"c7fa2360efd5683c6cd994d5618762b2e938cdd4858ed7a60278d49db6a0574c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0XoUdqmFvLFcfD2klYvSyAZsbB5mrJsuuCr1j3KyuZtiRvw9Ebj4ylnEPpKLPS3NIPnO/MZHlw84s9FEmDIrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:34:06.179776Z","bundle_sha256":"479211d1ca832861783a3b5724b99069ba69b77d46559e3b88164a5c28df5b91"}}