{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7R6UF57KUOCASFIL6RP74CNXUW","short_pith_number":"pith:7R6UF57K","canonical_record":{"source":{"id":"2004.13379","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T09:15:50Z","cross_cats_sorted":[],"title_canon_sha256":"6650d8432184f49bf7a8684c2af095333a12f40ee1ccddfbacaf035b09476129","abstract_canon_sha256":"ec9f22cd9f68ba49ad5d28c28f97350a851830a18c3a8c9a516586c7ed3a9b44"},"schema_version":"1.0"},"canonical_sha256":"fc7d42f7eaa38409150bf45ffe09b7a5a2b358057382a1753bb8854599898523","source":{"kind":"arxiv","id":"2004.13379","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13379","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13379v3","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13379","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"7R6UF57KUOCA","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"7R6UF57KUOCASFIL","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"7R6UF57K","created_at":"2026-07-05T02:09:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7R6UF57KUOCASFIL6RP74CNXUW","target":"record","payload":{"canonical_record":{"source":{"id":"2004.13379","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T09:15:50Z","cross_cats_sorted":[],"title_canon_sha256":"6650d8432184f49bf7a8684c2af095333a12f40ee1ccddfbacaf035b09476129","abstract_canon_sha256":"ec9f22cd9f68ba49ad5d28c28f97350a851830a18c3a8c9a516586c7ed3a9b44"},"schema_version":"1.0"},"canonical_sha256":"fc7d42f7eaa38409150bf45ffe09b7a5a2b358057382a1753bb8854599898523","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:09.879000Z","signature_b64":"HVsvtGqtiPnatGfGPBp/73qdC9gScSCJMog7FWgT/3QsFtDPz1x//JbVi9OTcqAHvqk1FJOJjlADuAU3QgT0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc7d42f7eaa38409150bf45ffe09b7a5a2b358057382a1753bb8854599898523","last_reissued_at":"2026-07-05T02:09:09.878528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:09.878528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.13379","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFQ4qGT+xQgN390/zj3cWn7avkPrPvZjydc+kM4TzoYseysesCpARo3xc4ugvfFbdKa6QIFfuDoBfqEqYd9NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:06:38.410409Z"},"content_sha256":"fc43595bf340660986aa46e9fcb19714a43d2e49557636825ad71cd2d6987605","schema_version":"1.0","event_id":"sha256:fc43595bf340660986aa46e9fcb19714a43d2e49557636825ad71cd2d6987605"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7R6UF57KUOCASFIL6RP74CNXUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Learning for Dense Prediction Tasks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Luc Van Gool, Marc Proesmans, Simon Vandenhende, Stamatios Georgoulis, Wouter Van Gansbeke","submitted_at":"2020-04-28T09:15:50Z","abstract_excerpt":"With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach is to learn these tasks in isolation, that is, a separate neural network is trained for each individual task. Yet, recent multi-task learning (MTL) techniques have shown promising results w.r.t. performance, computations and/or memory footprint, by jointly tackling multiple tasks through a learned shared representation. In this survey, we provide a well-rounded view on state-of-the-art deep learning approaches for M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13379","kind":"arxiv","version":3},"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/2004.13379/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":"2026-07-05T02:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GuU4kIKhS5rSaRT8wy9caf+G0VK6GTgcnwyo8xf9Vi4LDDaAhB9sAT1ROqSsm677i1AvvDGbMnynE4sakD9aAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:06:38.411333Z"},"content_sha256":"9755c4081b86afcd747723a169f8ca668fed19ee3cb75ced65ab9fdd3c23f43d","schema_version":"1.0","event_id":"sha256:9755c4081b86afcd747723a169f8ca668fed19ee3cb75ced65ab9fdd3c23f43d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7R6UF57KUOCASFIL6RP74CNXUW/bundle.json","state_url":"https://pith.science/pith/7R6UF57KUOCASFIL6RP74CNXUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7R6UF57KUOCASFIL6RP74CNXUW/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":"2026-08-14T19:06:38Z","links":{"resolver":"https://pith.science/pith/7R6UF57KUOCASFIL6RP74CNXUW","bundle":"https://pith.science/pith/7R6UF57KUOCASFIL6RP74CNXUW/bundle.json","state":"https://pith.science/pith/7R6UF57KUOCASFIL6RP74CNXUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7R6UF57KUOCASFIL6RP74CNXUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7R6UF57KUOCASFIL6RP74CNXUW","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":"ec9f22cd9f68ba49ad5d28c28f97350a851830a18c3a8c9a516586c7ed3a9b44","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T09:15:50Z","title_canon_sha256":"6650d8432184f49bf7a8684c2af095333a12f40ee1ccddfbacaf035b09476129"},"schema_version":"1.0","source":{"id":"2004.13379","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13379","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13379v3","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13379","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"7R6UF57KUOCA","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"7R6UF57KUOCASFIL","created_at":"2026-07-05T02:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"7R6UF57K","created_at":"2026-07-05T02:09:09Z"}],"graph_snapshots":[{"event_id":"sha256:9755c4081b86afcd747723a169f8ca668fed19ee3cb75ced65ab9fdd3c23f43d","target":"graph","created_at":"2026-07-05T02:09:09Z","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/2004.13379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach is to learn these tasks in isolation, that is, a separate neural network is trained for each individual task. Yet, recent multi-task learning (MTL) techniques have shown promising results w.r.t. performance, computations and/or memory footprint, by jointly tackling multiple tasks through a learned shared representation. In this survey, we provide a well-rounded view on state-of-the-art deep learning approaches for M","authors_text":"Dengxin Dai, Luc Van Gool, Marc Proesmans, Simon Vandenhende, Stamatios Georgoulis, Wouter Van Gansbeke","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T09:15:50Z","title":"Multi-Task Learning for Dense Prediction Tasks: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13379","kind":"arxiv","version":3},"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:fc43595bf340660986aa46e9fcb19714a43d2e49557636825ad71cd2d6987605","target":"record","created_at":"2026-07-05T02:09:09Z","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":"ec9f22cd9f68ba49ad5d28c28f97350a851830a18c3a8c9a516586c7ed3a9b44","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T09:15:50Z","title_canon_sha256":"6650d8432184f49bf7a8684c2af095333a12f40ee1ccddfbacaf035b09476129"},"schema_version":"1.0","source":{"id":"2004.13379","kind":"arxiv","version":3}},"canonical_sha256":"fc7d42f7eaa38409150bf45ffe09b7a5a2b358057382a1753bb8854599898523","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc7d42f7eaa38409150bf45ffe09b7a5a2b358057382a1753bb8854599898523","first_computed_at":"2026-07-05T02:09:09.878528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:09:09.878528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HVsvtGqtiPnatGfGPBp/73qdC9gScSCJMog7FWgT/3QsFtDPz1x//JbVi9OTcqAHvqk1FJOJjlADuAU3QgT0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:09:09.879000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.13379","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc43595bf340660986aa46e9fcb19714a43d2e49557636825ad71cd2d6987605","sha256:9755c4081b86afcd747723a169f8ca668fed19ee3cb75ced65ab9fdd3c23f43d"],"state_sha256":"65287b2e6c1de751df713a9648576410b3ef9df872ded5a886bc10ab461c82cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p+mXhaT4ea1bZzkKh4O36HOPCpYvoboGW6g+ruAiEgHf11pdFISzf+hIIgp/48tReQEHy5Az3FW9Id972GpvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:06:38.422852Z","bundle_sha256":"f68e0617f568ffb579aac426aa87a8d8bafd2f07f798eee0b3809d965eca8c25"}}