{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:L52Q3R7BXOLVKSB5ZB6DUYFTQ7","short_pith_number":"pith:L52Q3R7B","canonical_record":{"source":{"id":"2109.04617","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T02:01:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"85114284bb27392ebc60c4206afe67d141035ce2563e727b5318ceda2e44dd90","abstract_canon_sha256":"acbb955428e72bf99d5eb88c624c7efb1aa167343315b86a2d3115f0a5494ef0"},"schema_version":"1.0"},"canonical_sha256":"5f750dc7e1bb9755483dc87c3a60b387f952044db4f1f8af6df4e57f3b25a705","source":{"kind":"arxiv","id":"2109.04617","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04617","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04617v2","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04617","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"L52Q3R7BXOLV","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"L52Q3R7BXOLVKSB5","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"L52Q3R7B","created_at":"2026-07-05T03:25:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:L52Q3R7BXOLVKSB5ZB6DUYFTQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2109.04617","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T02:01:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"85114284bb27392ebc60c4206afe67d141035ce2563e727b5318ceda2e44dd90","abstract_canon_sha256":"acbb955428e72bf99d5eb88c624c7efb1aa167343315b86a2d3115f0a5494ef0"},"schema_version":"1.0"},"canonical_sha256":"5f750dc7e1bb9755483dc87c3a60b387f952044db4f1f8af6df4e57f3b25a705","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:34.337604Z","signature_b64":"nXYpJlnkv7eBzS6nHCYnZRgJkBuO9rgqtECF+IJ71A56z0ZtxttulPzXRlnYjAx5EPNN9GjUd2ppNq+COStdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f750dc7e1bb9755483dc87c3a60b387f952044db4f1f8af6df4e57f3b25a705","last_reissued_at":"2026-07-05T03:25:34.337203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:34.337203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.04617","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":"2026-07-05T03:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bMpr4Y0T3OtFzq2Aw5XXP2IPC395xB8z16W3B83w0lSShqTWgmJ8hPywZ6TywzjXCTuEi9ILacHWsQtyBZUXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T00:42:35.893964Z"},"content_sha256":"bbf200f16593f02b204ecf493a38443f5f3de99e8cef81b0a570bdf7d8faeeb7","schema_version":"1.0","event_id":"sha256:bbf200f16593f02b204ecf493a38443f5f3de99e8cef81b0a570bdf7d8faeeb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:L52Q3R7BXOLVKSB5ZB6DUYFTQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficiently Identifying Task Groupings for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Christopher Fifty, Ehsan Amid, Rohan Anil, Tianhe Yu, Zhe Zhao","submitted_at":"2021-09-10T02:01:43Z","abstract_excerpt":"Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through combinations of task groupings can be prohibitively expensive. As a result, efficiently identifying the tasks that would benefit from training together remains a challenging design question without a clear solution. In this paper, we suggest an approach to select which tasks should train together in multi-task learning models. Our method determines task grou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04617","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/2109.04617/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":"2026-07-05T03:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3clSfjUUhEHMSGsKWrCa6EgLZlNNY2rKNbembAI1raSFWiGXYOlKNg5KwBBnDqUtCWO3lrJjG8mf4hWFh6eAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T00:42:35.894562Z"},"content_sha256":"9ea094b7d27c3614ce3fee52d2df2e0a50d3285a56bf398e739832917f65b3de","schema_version":"1.0","event_id":"sha256:9ea094b7d27c3614ce3fee52d2df2e0a50d3285a56bf398e739832917f65b3de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L52Q3R7BXOLVKSB5ZB6DUYFTQ7/bundle.json","state_url":"https://pith.science/pith/L52Q3R7BXOLVKSB5ZB6DUYFTQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L52Q3R7BXOLVKSB5ZB6DUYFTQ7/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":"2026-08-13T00:42:35Z","links":{"resolver":"https://pith.science/pith/L52Q3R7BXOLVKSB5ZB6DUYFTQ7","bundle":"https://pith.science/pith/L52Q3R7BXOLVKSB5ZB6DUYFTQ7/bundle.json","state":"https://pith.science/pith/L52Q3R7BXOLVKSB5ZB6DUYFTQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L52Q3R7BXOLVKSB5ZB6DUYFTQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:L52Q3R7BXOLVKSB5ZB6DUYFTQ7","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":"acbb955428e72bf99d5eb88c624c7efb1aa167343315b86a2d3115f0a5494ef0","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T02:01:43Z","title_canon_sha256":"85114284bb27392ebc60c4206afe67d141035ce2563e727b5318ceda2e44dd90"},"schema_version":"1.0","source":{"id":"2109.04617","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04617","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04617v2","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04617","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"L52Q3R7BXOLV","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"L52Q3R7BXOLVKSB5","created_at":"2026-07-05T03:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"L52Q3R7B","created_at":"2026-07-05T03:25:34Z"}],"graph_snapshots":[{"event_id":"sha256:9ea094b7d27c3614ce3fee52d2df2e0a50d3285a56bf398e739832917f65b3de","target":"graph","created_at":"2026-07-05T03:25:34Z","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/2109.04617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through combinations of task groupings can be prohibitively expensive. As a result, efficiently identifying the tasks that would benefit from training together remains a challenging design question without a clear solution. In this paper, we suggest an approach to select which tasks should train together in multi-task learning models. Our method determines task grou","authors_text":"Chelsea Finn, Christopher Fifty, Ehsan Amid, Rohan Anil, Tianhe Yu, Zhe Zhao","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T02:01:43Z","title":"Efficiently Identifying Task Groupings for Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04617","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:bbf200f16593f02b204ecf493a38443f5f3de99e8cef81b0a570bdf7d8faeeb7","target":"record","created_at":"2026-07-05T03:25:34Z","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":"acbb955428e72bf99d5eb88c624c7efb1aa167343315b86a2d3115f0a5494ef0","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T02:01:43Z","title_canon_sha256":"85114284bb27392ebc60c4206afe67d141035ce2563e727b5318ceda2e44dd90"},"schema_version":"1.0","source":{"id":"2109.04617","kind":"arxiv","version":2}},"canonical_sha256":"5f750dc7e1bb9755483dc87c3a60b387f952044db4f1f8af6df4e57f3b25a705","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f750dc7e1bb9755483dc87c3a60b387f952044db4f1f8af6df4e57f3b25a705","first_computed_at":"2026-07-05T03:25:34.337203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:34.337203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nXYpJlnkv7eBzS6nHCYnZRgJkBuO9rgqtECF+IJ71A56z0ZtxttulPzXRlnYjAx5EPNN9GjUd2ppNq+COStdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:34.337604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04617","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbf200f16593f02b204ecf493a38443f5f3de99e8cef81b0a570bdf7d8faeeb7","sha256:9ea094b7d27c3614ce3fee52d2df2e0a50d3285a56bf398e739832917f65b3de"],"state_sha256":"994e2cc63c254d6eb5530fe841f7980f4b7d54abdc274d0c53e3510e45495af6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9TBk6o+z/toP1eM69vBAKJyDyuhB81gY4+RwK9tscVzTVcSv6gxnfyoHTuXxWvVSsmTwkp04X6I/prWlzsRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T00:42:35.900313Z","bundle_sha256":"205e99e1c9083750705af701d07b21c70cc90e564b90a6ee475876e19cb23a98"}}