{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:LKP3STKVPLCTADMMC77A6ND2HB","short_pith_number":"pith:LKP3STKV","canonical_record":{"source":{"id":"1209.2784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-09-13T06:14:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"05ffe47f508b62e57b758f450498bdb369f599f9f747ecb8abd4baa5b2c5d861","abstract_canon_sha256":"f7d646ea20f2930adb3c69b977bce12440b6ae4bc133cbd38175ba9030d8a5b3"},"schema_version":"1.0"},"canonical_sha256":"5a9fb94d557ac5300d8c17fe0f347a38599148e89ca2802e1cdb9fb0ef6a900c","source":{"kind":"arxiv","id":"1209.2784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1209.2784","created_at":"2026-05-18T03:45:40Z"},{"alias_kind":"arxiv_version","alias_value":"1209.2784v1","created_at":"2026-05-18T03:45:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1209.2784","created_at":"2026-05-18T03:45:40Z"},{"alias_kind":"pith_short_12","alias_value":"LKP3STKVPLCT","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"LKP3STKVPLCTADMM","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"LKP3STKV","created_at":"2026-05-18T12:27:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:LKP3STKVPLCTADMMC77A6ND2HB","target":"record","payload":{"canonical_record":{"source":{"id":"1209.2784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-09-13T06:14:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"05ffe47f508b62e57b758f450498bdb369f599f9f747ecb8abd4baa5b2c5d861","abstract_canon_sha256":"f7d646ea20f2930adb3c69b977bce12440b6ae4bc133cbd38175ba9030d8a5b3"},"schema_version":"1.0"},"canonical_sha256":"5a9fb94d557ac5300d8c17fe0f347a38599148e89ca2802e1cdb9fb0ef6a900c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:45:40.989479Z","signature_b64":"vqyiLsQDdqgFQ/Vnm70v63BVPYWQu3ejK7QHv6akP6RjQTALo9b/lYk4+60F+Iua0n8cp0WiM2wQh0p5IJGdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a9fb94d557ac5300d8c17fe0f347a38599148e89ca2802e1cdb9fb0ef6a900c","last_reissued_at":"2026-05-18T03:45:40.988829Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:45:40.988829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1209.2784","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":"2026-05-18T03:45:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dH3lNb5BriFfEVxHqd7uDwu3OhhvxZhnpCZLIPmgF3qSIOO2Kb/95PkzzhZ0Wno5RxS8rVgFcg4Grld6l/ETAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:24:25.745537Z"},"content_sha256":"94af4c7ce339158a2c823a9dcdf6f28d0b1795f5b14f769d9b692c5713723618","schema_version":"1.0","event_id":"sha256:94af4c7ce339158a2c823a9dcdf6f28d0b1795f5b14f769d9b692c5713723618"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:LKP3STKVPLCTADMMC77A6ND2HB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimax Multi-Task Learning and a Generalized Loss-Compositional Paradigm for MTL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander G. Gray, Dongryeol Lee, Nishant A. Mehta","submitted_at":"2012-09-13T06:14:31Z","abstract_excerpt":"Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that includes a spectrum of formulations as a subfamily. One endpoint of this spectrum is minimax MTL: a new MTL formulation that minimizes the maximum of the tasks' empirical risks. Via a certain relaxation of minimax MTL, we obtain a continuum of MTL formulations spanning minimax MTL and classical MTL. The full paradigm itself is loss-compositional, operating on the vector of empirical risks. It inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1209.2784","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":""},"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":"2026-05-18T03:45:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rAquKVt2SkZT7cz4psmfA6W3S0z5nQErrrkrLBRyHC9frALzeaqczGcqP9AzcUFq0nSSF0fllBZ/JlnJ1WgpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:24:25.745887Z"},"content_sha256":"88fd50827e2b9d57f03dd70b9f322cb2002d45434ac5869ddca4c9185c1b6e78","schema_version":"1.0","event_id":"sha256:88fd50827e2b9d57f03dd70b9f322cb2002d45434ac5869ddca4c9185c1b6e78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKP3STKVPLCTADMMC77A6ND2HB/bundle.json","state_url":"https://pith.science/pith/LKP3STKVPLCTADMMC77A6ND2HB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKP3STKVPLCTADMMC77A6ND2HB/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":"2026-06-03T07:24:25Z","links":{"resolver":"https://pith.science/pith/LKP3STKVPLCTADMMC77A6ND2HB","bundle":"https://pith.science/pith/LKP3STKVPLCTADMMC77A6ND2HB/bundle.json","state":"https://pith.science/pith/LKP3STKVPLCTADMMC77A6ND2HB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKP3STKVPLCTADMMC77A6ND2HB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:LKP3STKVPLCTADMMC77A6ND2HB","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":"f7d646ea20f2930adb3c69b977bce12440b6ae4bc133cbd38175ba9030d8a5b3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-09-13T06:14:31Z","title_canon_sha256":"05ffe47f508b62e57b758f450498bdb369f599f9f747ecb8abd4baa5b2c5d861"},"schema_version":"1.0","source":{"id":"1209.2784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1209.2784","created_at":"2026-05-18T03:45:40Z"},{"alias_kind":"arxiv_version","alias_value":"1209.2784v1","created_at":"2026-05-18T03:45:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1209.2784","created_at":"2026-05-18T03:45:40Z"},{"alias_kind":"pith_short_12","alias_value":"LKP3STKVPLCT","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"LKP3STKVPLCTADMM","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"LKP3STKV","created_at":"2026-05-18T12:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:88fd50827e2b9d57f03dd70b9f322cb2002d45434ac5869ddca4c9185c1b6e78","target":"graph","created_at":"2026-05-18T03:45:40Z","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"},"paper":{"abstract_excerpt":"Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that includes a spectrum of formulations as a subfamily. One endpoint of this spectrum is minimax MTL: a new MTL formulation that minimizes the maximum of the tasks' empirical risks. Via a certain relaxation of minimax MTL, we obtain a continuum of MTL formulations spanning minimax MTL and classical MTL. The full paradigm itself is loss-compositional, operating on the vector of empirical risks. It inc","authors_text":"Alexander G. Gray, Dongryeol Lee, Nishant A. Mehta","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-09-13T06:14:31Z","title":"Minimax Multi-Task Learning and a Generalized Loss-Compositional Paradigm for MTL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1209.2784","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":"sha256:94af4c7ce339158a2c823a9dcdf6f28d0b1795f5b14f769d9b692c5713723618","target":"record","created_at":"2026-05-18T03:45:40Z","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":"f7d646ea20f2930adb3c69b977bce12440b6ae4bc133cbd38175ba9030d8a5b3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-09-13T06:14:31Z","title_canon_sha256":"05ffe47f508b62e57b758f450498bdb369f599f9f747ecb8abd4baa5b2c5d861"},"schema_version":"1.0","source":{"id":"1209.2784","kind":"arxiv","version":1}},"canonical_sha256":"5a9fb94d557ac5300d8c17fe0f347a38599148e89ca2802e1cdb9fb0ef6a900c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a9fb94d557ac5300d8c17fe0f347a38599148e89ca2802e1cdb9fb0ef6a900c","first_computed_at":"2026-05-18T03:45:40.988829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:45:40.988829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vqyiLsQDdqgFQ/Vnm70v63BVPYWQu3ejK7QHv6akP6RjQTALo9b/lYk4+60F+Iua0n8cp0WiM2wQh0p5IJGdAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:45:40.989479Z","signed_message":"canonical_sha256_bytes"},"source_id":"1209.2784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94af4c7ce339158a2c823a9dcdf6f28d0b1795f5b14f769d9b692c5713723618","sha256:88fd50827e2b9d57f03dd70b9f322cb2002d45434ac5869ddca4c9185c1b6e78"],"state_sha256":"2e86fd6df5f28792f32b6f796f424b2dd574e3be9111b958786376c77f749f56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbWwVKycXtnIRt0x06C2ACU4pBS+kNHsPXyQGfE8KXKQOqoqOuD8hUP7wjXuv4yw1lcItOapJaoTZr1Cfi2TAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:24:25.747946Z","bundle_sha256":"89edf2290686e7807931b2bb383bfb96172a9fb2489a4c5628e19ae39ceef580"}}