{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:O2XWDQYPLXE6CV52XQDJ2OSBAU","short_pith_number":"pith:O2XWDQYP","schema_version":"1.0","canonical_sha256":"76af61c30f5dc9e157babc069d3a410533401cd578e001d8f3ec5a37f1dcb0b1","source":{"kind":"arxiv","id":"1904.02920","version":5},"attestation_state":"computed","paper":{"title":"Branched Multi-Task Networks: Deciding What Layers To Share","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert De Brabandere, Luc Van Gool, Simon Vandenhende, Stamatios Georgoulis","submitted_at":"2019-04-05T08:00:32Z","abstract_excerpt":"In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. Understandably, as the number of possible network configurations is combinatorially large, deciding what layers to share and where to branch out becomes cumbersome. Prior works have either relied on ad hoc methods to determine the level of layer sharing, which is suboptimal, or utilized neural architecture se"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.02920","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-05T08:00:32Z","cross_cats_sorted":[],"title_canon_sha256":"10106d1ea2414d0119eea8202d79ab4d83e92f21baee06c2e8a492e02ff270d7","abstract_canon_sha256":"fe004e7a821184566a93b2e434b860c0b3b543e8955e00ed255d8a2b99d16185"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:48.361949Z","signature_b64":"lwsn4gTyIMgYilYfy0nWM70hosIKN0OPoHvCELlOji2hXg9DqI2SWKV2vhWXN5e3lvt8SSDkM4AXd9Q0ouSeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76af61c30f5dc9e157babc069d3a410533401cd578e001d8f3ec5a37f1dcb0b1","last_reissued_at":"2026-07-05T01:26:48.361442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:48.361442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Branched Multi-Task Networks: Deciding What Layers To Share","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert De Brabandere, Luc Van Gool, Simon Vandenhende, Stamatios Georgoulis","submitted_at":"2019-04-05T08:00:32Z","abstract_excerpt":"In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. Understandably, as the number of possible network configurations is combinatorially large, deciding what layers to share and where to branch out becomes cumbersome. Prior works have either relied on ad hoc methods to determine the level of layer sharing, which is suboptimal, or utilized neural architecture se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02920","kind":"arxiv","version":5},"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/1904.02920/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.02920","created_at":"2026-07-05T01:26:48.361504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02920v5","created_at":"2026-07-05T01:26:48.361504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02920","created_at":"2026-07-05T01:26:48.361504+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2XWDQYPLXE6","created_at":"2026-07-05T01:26:48.361504+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2XWDQYPLXE6CV52","created_at":"2026-07-05T01:26:48.361504+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2XWDQYP","created_at":"2026-07-05T01:26:48.361504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07485","citing_title":"Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU","json":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU.json","graph_json":"https://pith.science/api/pith-number/O2XWDQYPLXE6CV52XQDJ2OSBAU/graph.json","events_json":"https://pith.science/api/pith-number/O2XWDQYPLXE6CV52XQDJ2OSBAU/events.json","paper":"https://pith.science/paper/O2XWDQYP"},"agent_actions":{"view_html":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU","download_json":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU.json","view_paper":"https://pith.science/paper/O2XWDQYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02920&json=true","fetch_graph":"https://pith.science/api/pith-number/O2XWDQYPLXE6CV52XQDJ2OSBAU/graph.json","fetch_events":"https://pith.science/api/pith-number/O2XWDQYPLXE6CV52XQDJ2OSBAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU/action/storage_attestation","attest_author":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU/action/author_attestation","sign_citation":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU/action/citation_signature","submit_replication":"https://pith.science/pith/O2XWDQYPLXE6CV52XQDJ2OSBAU/action/replication_record"}},"created_at":"2026-07-05T01:26:48.361504+00:00","updated_at":"2026-07-05T01:26:48.361504+00:00"}