{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GCEAUYYPJLSTACLGSTGDOQAEDP","short_pith_number":"pith:GCEAUYYP","canonical_record":{"source":{"id":"2306.04519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T15:29:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec91619bad9db8c3d2f5b50e686156d3f6b4326d99aba36793befce6748de3bb","abstract_canon_sha256":"a3067d799d156259dc945378ef5f3f30d3c88273350a01610a974409b3fe8c2b"},"schema_version":"1.0"},"canonical_sha256":"30880a630f4ae530096694cc3740041be649afab66d57890678745433b1ff2dc","source":{"kind":"arxiv","id":"2306.04519","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04519","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04519v1","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04519","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"GCEAUYYPJLST","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"GCEAUYYPJLSTACLG","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"GCEAUYYP","created_at":"2026-07-05T06:18:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GCEAUYYPJLSTACLGSTGDOQAEDP","target":"record","payload":{"canonical_record":{"source":{"id":"2306.04519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T15:29:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec91619bad9db8c3d2f5b50e686156d3f6b4326d99aba36793befce6748de3bb","abstract_canon_sha256":"a3067d799d156259dc945378ef5f3f30d3c88273350a01610a974409b3fe8c2b"},"schema_version":"1.0"},"canonical_sha256":"30880a630f4ae530096694cc3740041be649afab66d57890678745433b1ff2dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:31.732734Z","signature_b64":"CUppDrjuiSZlFBNgfpgsR6Dsbt4FsfPnxT5qvtZ1O1p+aPCKYW/ib7NW+Pi6ffJvyRbzOnCIy/xD1WlqTlhrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30880a630f4ae530096694cc3740041be649afab66d57890678745433b1ff2dc","last_reissued_at":"2026-07-05T06:18:31.732267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:31.732267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.04519","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":"2026-07-05T06:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wKojQux2TMAb/ow16EC2qU5Rq5XzpB1oBOxQDKQb3mBnxp0t1eMHz8ajunldvkkTwHIwemOIOSRbpWS/eZmzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:57:40.713287Z"},"content_sha256":"963754ab6377b7e052d46c2a042370ba9a589adf0155b2d6be7598de774d293c","schema_version":"1.0","event_id":"sha256:963754ab6377b7e052d46c2a042370ba9a589adf0155b2d6be7598de774d293c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GCEAUYYPJLSTACLGSTGDOQAEDP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emilie Gr\\'egoire, Hafeez Chaudhary, Sam Verboven","submitted_at":"2023-06-07T15:29:46Z","abstract_excerpt":"Multi-task learning (MTL) can improve the generalization performance of neural networks by sharing representations with related tasks. Nonetheless, MTL can also degrade performance through harmful interference between tasks. Recent work has pursued task-specific loss weighting as a solution for this interference. However, existing algorithms treat tasks as atomic, lacking the ability to explicitly separate harmful and helpful signals beyond the task level. To this end, we propose SLGrad, a sample-level weighting algorithm for multi-task learning with auxiliary tasks. Through sample-specific ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04519","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.04519/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":"2026-07-05T06:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NDIE6kYNQH/P2xO7cFFrZ5/OY7t5+shRAqjP3C5MUerSNqFqk9590sCRBxeHbQ8c6nzK4R9q2zoPA7ZnUDy5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:57:40.713677Z"},"content_sha256":"5cee010be9d95765ee1deaba92c141688d579b65537d04635196eeea03ecd138","schema_version":"1.0","event_id":"sha256:5cee010be9d95765ee1deaba92c141688d579b65537d04635196eeea03ecd138"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCEAUYYPJLSTACLGSTGDOQAEDP/bundle.json","state_url":"https://pith.science/pith/GCEAUYYPJLSTACLGSTGDOQAEDP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCEAUYYPJLSTACLGSTGDOQAEDP/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":"2026-08-05T02:57:40Z","links":{"resolver":"https://pith.science/pith/GCEAUYYPJLSTACLGSTGDOQAEDP","bundle":"https://pith.science/pith/GCEAUYYPJLSTACLGSTGDOQAEDP/bundle.json","state":"https://pith.science/pith/GCEAUYYPJLSTACLGSTGDOQAEDP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCEAUYYPJLSTACLGSTGDOQAEDP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GCEAUYYPJLSTACLGSTGDOQAEDP","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":"a3067d799d156259dc945378ef5f3f30d3c88273350a01610a974409b3fe8c2b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T15:29:46Z","title_canon_sha256":"ec91619bad9db8c3d2f5b50e686156d3f6b4326d99aba36793befce6748de3bb"},"schema_version":"1.0","source":{"id":"2306.04519","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04519","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04519v1","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04519","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"GCEAUYYPJLST","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"GCEAUYYPJLSTACLG","created_at":"2026-07-05T06:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"GCEAUYYP","created_at":"2026-07-05T06:18:31Z"}],"graph_snapshots":[{"event_id":"sha256:5cee010be9d95765ee1deaba92c141688d579b65537d04635196eeea03ecd138","target":"graph","created_at":"2026-07-05T06:18:31Z","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/2306.04519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning (MTL) can improve the generalization performance of neural networks by sharing representations with related tasks. Nonetheless, MTL can also degrade performance through harmful interference between tasks. Recent work has pursued task-specific loss weighting as a solution for this interference. However, existing algorithms treat tasks as atomic, lacking the ability to explicitly separate harmful and helpful signals beyond the task level. To this end, we propose SLGrad, a sample-level weighting algorithm for multi-task learning with auxiliary tasks. Through sample-specific ta","authors_text":"Emilie Gr\\'egoire, Hafeez Chaudhary, Sam Verboven","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T15:29:46Z","title":"Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04519","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":"sha256:963754ab6377b7e052d46c2a042370ba9a589adf0155b2d6be7598de774d293c","target":"record","created_at":"2026-07-05T06:18:31Z","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":"a3067d799d156259dc945378ef5f3f30d3c88273350a01610a974409b3fe8c2b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T15:29:46Z","title_canon_sha256":"ec91619bad9db8c3d2f5b50e686156d3f6b4326d99aba36793befce6748de3bb"},"schema_version":"1.0","source":{"id":"2306.04519","kind":"arxiv","version":1}},"canonical_sha256":"30880a630f4ae530096694cc3740041be649afab66d57890678745433b1ff2dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30880a630f4ae530096694cc3740041be649afab66d57890678745433b1ff2dc","first_computed_at":"2026-07-05T06:18:31.732267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:31.732267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CUppDrjuiSZlFBNgfpgsR6Dsbt4FsfPnxT5qvtZ1O1p+aPCKYW/ib7NW+Pi6ffJvyRbzOnCIy/xD1WlqTlhrAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:31.732734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04519","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:963754ab6377b7e052d46c2a042370ba9a589adf0155b2d6be7598de774d293c","sha256:5cee010be9d95765ee1deaba92c141688d579b65537d04635196eeea03ecd138"],"state_sha256":"4e8c36bd400371bef79b8b43bf8b54ff3992310466e1ab101a1ab4fdfaf2cef5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oo1fNNqtM8r9I7HtT5QHlQ0aULVOtC6SR1QloCbeNcOK57qIDz7XYYWH5cFqq477BjWDq5WstBC6CrwchO4KAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:57:40.716157Z","bundle_sha256":"f552b6fe4a48a85b212d3352d65724aa8108c5bf3ffc853f9e2362e4d577d1df"}}