{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GUOGVEBGUGOU5VEO2OX2LP6KA7","short_pith_number":"pith:GUOGVEBG","canonical_record":{"source":{"id":"1904.04153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T16:05:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3521a76753dd796c031e54290135acf51d8f909c2bd7c15c3a18874489cc2f0e","abstract_canon_sha256":"6b3b8dad75639e30616e85f4e83f9e7aeb6d99ac72fee37233355acf6a479cb4"},"schema_version":"1.0"},"canonical_sha256":"351c6a9026a19d4ed48ed3afa5bfca07c5d3ac020f1a1b495bca2d17b5550ce5","source":{"kind":"arxiv","id":"1904.04153","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04153","created_at":"2026-05-17T23:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04153v1","created_at":"2026-05-17T23:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04153","created_at":"2026-05-17T23:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"GUOGVEBGUGOU","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GUOGVEBGUGOU5VEO","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GUOGVEBG","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GUOGVEBGUGOU5VEO2OX2LP6KA7","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T16:05:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3521a76753dd796c031e54290135acf51d8f909c2bd7c15c3a18874489cc2f0e","abstract_canon_sha256":"6b3b8dad75639e30616e85f4e83f9e7aeb6d99ac72fee37233355acf6a479cb4"},"schema_version":"1.0"},"canonical_sha256":"351c6a9026a19d4ed48ed3afa5bfca07c5d3ac020f1a1b495bca2d17b5550ce5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:06.949414Z","signature_b64":"has3gYZZkjxVEHLxgFy3J9HlzbD4IV0CB3sur/ohc95hMDs5JAZ7v5fG3k0PoeyFy8sIkT2c/kIAO3bft0lsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"351c6a9026a19d4ed48ed3afa5bfca07c5d3ac020f1a1b495bca2d17b5550ce5","last_reissued_at":"2026-05-17T23:49:06.948723Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:06.948723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04153","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":"2026-05-17T23:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/hlPVjBX39LiATaNGV/4vurVoRWdBTYtSy0pLYmmEym8sOI2lpCF+c0D2xRUSKEwOrckBk+rXtl5bi6llgVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:11:51.845251Z"},"content_sha256":"a1e38c1c622982f9a185bad4048fe5b4c71bb7f737393cb2918f141a7e6da706","schema_version":"1.0","event_id":"sha256:a1e38c1c622982f9a185bad4048fe5b4c71bb7f737393cb2918f141a7e6da706"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GUOGVEBGUGOU5VEO2OX2LP6KA7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Han Guo, Mohit Bansal, Ramakanth Pasunuru","submitted_at":"2019-04-08T16:05:43Z","abstract_excerpt":"Multi-task learning (MTL) has achieved success over a wide range of problems, where the goal is to improve the performance of a primary task using a set of relevant auxiliary tasks. However, when the usefulness of the auxiliary tasks w.r.t. the primary task is not known a priori, the success of MTL models depends on the correct choice of these auxiliary tasks and also a balanced mixing ratio of these tasks during alternate training. These two problems could be resolved via manual intuition or hyper-parameter tuning over all combinatorial task choices, but this introduces inductive bias or is n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04153","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":"2026-05-17T23:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQ6BEeTtXk5oxzyfbL/F8R29hNKmpRxa0DF0nIrir4LnZY69m1ZW0mifhqprng7YFk3ifRcaunvDUkfb18VuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:11:51.845618Z"},"content_sha256":"0f5f1587f104c43ad184f8cc94f0ea92c60a1de8065d8f8e4d25728864876c89","schema_version":"1.0","event_id":"sha256:0f5f1587f104c43ad184f8cc94f0ea92c60a1de8065d8f8e4d25728864876c89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUOGVEBGUGOU5VEO2OX2LP6KA7/bundle.json","state_url":"https://pith.science/pith/GUOGVEBGUGOU5VEO2OX2LP6KA7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUOGVEBGUGOU5VEO2OX2LP6KA7/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":"2026-06-03T01:11:51Z","links":{"resolver":"https://pith.science/pith/GUOGVEBGUGOU5VEO2OX2LP6KA7","bundle":"https://pith.science/pith/GUOGVEBGUGOU5VEO2OX2LP6KA7/bundle.json","state":"https://pith.science/pith/GUOGVEBGUGOU5VEO2OX2LP6KA7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUOGVEBGUGOU5VEO2OX2LP6KA7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GUOGVEBGUGOU5VEO2OX2LP6KA7","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":"6b3b8dad75639e30616e85f4e83f9e7aeb6d99ac72fee37233355acf6a479cb4","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T16:05:43Z","title_canon_sha256":"3521a76753dd796c031e54290135acf51d8f909c2bd7c15c3a18874489cc2f0e"},"schema_version":"1.0","source":{"id":"1904.04153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04153","created_at":"2026-05-17T23:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04153v1","created_at":"2026-05-17T23:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04153","created_at":"2026-05-17T23:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"GUOGVEBGUGOU","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GUOGVEBGUGOU5VEO","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GUOGVEBG","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:0f5f1587f104c43ad184f8cc94f0ea92c60a1de8065d8f8e4d25728864876c89","target":"graph","created_at":"2026-05-17T23:49:06Z","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":"Multi-task learning (MTL) has achieved success over a wide range of problems, where the goal is to improve the performance of a primary task using a set of relevant auxiliary tasks. However, when the usefulness of the auxiliary tasks w.r.t. the primary task is not known a priori, the success of MTL models depends on the correct choice of these auxiliary tasks and also a balanced mixing ratio of these tasks during alternate training. These two problems could be resolved via manual intuition or hyper-parameter tuning over all combinatorial task choices, but this introduces inductive bias or is n","authors_text":"Han Guo, Mohit Bansal, Ramakanth Pasunuru","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T16:05:43Z","title":"AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04153","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:a1e38c1c622982f9a185bad4048fe5b4c71bb7f737393cb2918f141a7e6da706","target":"record","created_at":"2026-05-17T23:49:06Z","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":"6b3b8dad75639e30616e85f4e83f9e7aeb6d99ac72fee37233355acf6a479cb4","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T16:05:43Z","title_canon_sha256":"3521a76753dd796c031e54290135acf51d8f909c2bd7c15c3a18874489cc2f0e"},"schema_version":"1.0","source":{"id":"1904.04153","kind":"arxiv","version":1}},"canonical_sha256":"351c6a9026a19d4ed48ed3afa5bfca07c5d3ac020f1a1b495bca2d17b5550ce5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"351c6a9026a19d4ed48ed3afa5bfca07c5d3ac020f1a1b495bca2d17b5550ce5","first_computed_at":"2026-05-17T23:49:06.948723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:06.948723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"has3gYZZkjxVEHLxgFy3J9HlzbD4IV0CB3sur/ohc95hMDs5JAZ7v5fG3k0PoeyFy8sIkT2c/kIAO3bft0lsCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:06.949414Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1e38c1c622982f9a185bad4048fe5b4c71bb7f737393cb2918f141a7e6da706","sha256:0f5f1587f104c43ad184f8cc94f0ea92c60a1de8065d8f8e4d25728864876c89"],"state_sha256":"8d943cc102d6c5ea4b298a897ed5c3f53c28d883aaf9f19bc2ad21b423630a66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ms/VBriaISh1kPcw2vrqUOGOw2HjayyUEIygroFpE8LnZWX/YMztpwfauIBUnUW+71yEkcpcCuTLyh43VFcyAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T01:11:51.847590Z","bundle_sha256":"14b5e27950bd8c8200241be0eda7d12397656eb3b16e9b694dc8b5c8492da451"}}