{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JRRSJIXOEHMNN2AGSM4VM3TWGG","short_pith_number":"pith:JRRSJIXO","canonical_record":{"source":{"id":"1903.09171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T18:07:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"389d3c598c18f1ab7126e32697ff115cfd4716623ff98d34a529cb29ceaee19b","abstract_canon_sha256":"451b830f7819ef54598c3de98a573824cd107295077d1dbd3ef0625753d5e1d5"},"schema_version":"1.0"},"canonical_sha256":"4c6324a2ee21d8d6e8069339566e7631ab71fd1ff80e489364eebca94b71530d","source":{"kind":"arxiv","id":"1903.09171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09171","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09171v1","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09171","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"JRRSJIXOEHMN","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JRRSJIXOEHMNN2AG","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JRRSJIXO","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JRRSJIXOEHMNN2AGSM4VM3TWGG","target":"record","payload":{"canonical_record":{"source":{"id":"1903.09171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T18:07:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"389d3c598c18f1ab7126e32697ff115cfd4716623ff98d34a529cb29ceaee19b","abstract_canon_sha256":"451b830f7819ef54598c3de98a573824cd107295077d1dbd3ef0625753d5e1d5"},"schema_version":"1.0"},"canonical_sha256":"4c6324a2ee21d8d6e8069339566e7631ab71fd1ff80e489364eebca94b71530d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:40.427322Z","signature_b64":"V9e1nUUZIyFRWupv4Ysu5Lfdvaux4AxYrST0Uttt6JSYTlHluAvGd/Y4yPAJ6gYm8VTP6MyMSPyEd7n8KQSwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c6324a2ee21d8d6e8069339566e7631ab71fd1ff80e489364eebca94b71530d","last_reissued_at":"2026-05-17T23:50:40.426784Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:40.426784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.09171","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":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/tIObICmd9YReEW1rz23Wx6Q85lMpFbqOPGrD1vnNvJku5kFF8zcxz5lVGlX0S5RcZGu/nNGySh6esDl1wUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T12:45:09.389555Z"},"content_sha256":"28331efac7e6d7b48fdaf0c22c21ee8914c6d93606432ea775dd70b091f9e9e6","schema_version":"1.0","event_id":"sha256:28331efac7e6d7b48fdaf0c22c21ee8914c6d93606432ea775dd70b091f9e9e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JRRSJIXOEHMNN2AGSM4VM3TWGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards automatic construction of multi-network models for heterogeneous multi-task learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Mendiburu, Roberto Santana, Unai Garciarena","submitted_at":"2019-03-21T18:07:02Z","abstract_excerpt":"Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using reinforcement learning, multi-task models have been able to widen their performance range across different tasks, although these tasks are usually of a similar nature. In this work, we attempt to widen this range even further, by including heterogeneous tasks in a single learning procedure. To do so, we firstly formally define a multi-network model, identify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09171","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":"2026-05-17T23:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C79Wt6GJp4quzKmpmDzcFmh43rkNxwyUARt8rAX1Ny7NlBzg5uXDaLC7DIjQGhYf0iz5Hmr+mfut6nojkzVnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T12:45:09.389902Z"},"content_sha256":"eba158dc1a3b0ffa162ebf70f2a89e62ac5b78771780dcfdf632f27265db810c","schema_version":"1.0","event_id":"sha256:eba158dc1a3b0ffa162ebf70f2a89e62ac5b78771780dcfdf632f27265db810c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JRRSJIXOEHMNN2AGSM4VM3TWGG/bundle.json","state_url":"https://pith.science/pith/JRRSJIXOEHMNN2AGSM4VM3TWGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JRRSJIXOEHMNN2AGSM4VM3TWGG/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":"2026-06-28T12:45:09Z","links":{"resolver":"https://pith.science/pith/JRRSJIXOEHMNN2AGSM4VM3TWGG","bundle":"https://pith.science/pith/JRRSJIXOEHMNN2AGSM4VM3TWGG/bundle.json","state":"https://pith.science/pith/JRRSJIXOEHMNN2AGSM4VM3TWGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JRRSJIXOEHMNN2AGSM4VM3TWGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JRRSJIXOEHMNN2AGSM4VM3TWGG","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":"451b830f7819ef54598c3de98a573824cd107295077d1dbd3ef0625753d5e1d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T18:07:02Z","title_canon_sha256":"389d3c598c18f1ab7126e32697ff115cfd4716623ff98d34a529cb29ceaee19b"},"schema_version":"1.0","source":{"id":"1903.09171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09171","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09171v1","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09171","created_at":"2026-05-17T23:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"JRRSJIXOEHMN","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JRRSJIXOEHMNN2AG","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JRRSJIXO","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:eba158dc1a3b0ffa162ebf70f2a89e62ac5b78771780dcfdf632f27265db810c","target":"graph","created_at":"2026-05-17T23:50:40Z","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":"Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using reinforcement learning, multi-task models have been able to widen their performance range across different tasks, although these tasks are usually of a similar nature. In this work, we attempt to widen this range even further, by including heterogeneous tasks in a single learning procedure. To do so, we firstly formally define a multi-network model, identify","authors_text":"Alexander Mendiburu, Roberto Santana, Unai Garciarena","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T18:07:02Z","title":"Towards automatic construction of multi-network models for heterogeneous multi-task learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09171","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":"sha256:28331efac7e6d7b48fdaf0c22c21ee8914c6d93606432ea775dd70b091f9e9e6","target":"record","created_at":"2026-05-17T23:50:40Z","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":"451b830f7819ef54598c3de98a573824cd107295077d1dbd3ef0625753d5e1d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T18:07:02Z","title_canon_sha256":"389d3c598c18f1ab7126e32697ff115cfd4716623ff98d34a529cb29ceaee19b"},"schema_version":"1.0","source":{"id":"1903.09171","kind":"arxiv","version":1}},"canonical_sha256":"4c6324a2ee21d8d6e8069339566e7631ab71fd1ff80e489364eebca94b71530d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c6324a2ee21d8d6e8069339566e7631ab71fd1ff80e489364eebca94b71530d","first_computed_at":"2026-05-17T23:50:40.426784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:40.426784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V9e1nUUZIyFRWupv4Ysu5Lfdvaux4AxYrST0Uttt6JSYTlHluAvGd/Y4yPAJ6gYm8VTP6MyMSPyEd7n8KQSwDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:40.427322Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.09171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28331efac7e6d7b48fdaf0c22c21ee8914c6d93606432ea775dd70b091f9e9e6","sha256:eba158dc1a3b0ffa162ebf70f2a89e62ac5b78771780dcfdf632f27265db810c"],"state_sha256":"8c0b3c98f85fd9bbfc85b825f3b45e78ed287f38ccea5f1379854aeb8efc41ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zHjp6WVpLzZgYh2GOmWIVPiVp1vbtjrvhxfbZrnhdw2RH81jWBR8KT67WKB/W58BcHo7a72MxKcp6AhBNeJ/DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T12:45:09.391844Z","bundle_sha256":"c0800584fee7e943877d2754d5d9b3c4b91bac49a01a09ca486e1eb784f27aea"}}