{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IIO63B4EG7RY5UOHE46TMWP2RY","short_pith_number":"pith:IIO63B4E","schema_version":"1.0","canonical_sha256":"421ded878437e38ed1c7273d3659fa8e02d6500174ed9a1b4bebd821f8af3222","source":{"kind":"arxiv","id":"2210.08101","version":3},"attestation_state":"computed","paper":{"title":"Budget-Aware Pruning for Multi-Domain Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jurandy Almeida, Nicu Sebe, Rodrigo Berriel, Samuel Felipe dos Santos, Thiago Oliveira-Santos","submitted_at":"2022-10-14T20:48:12Z","abstract_excerpt":"Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such requirements hinder the use in resource-limited environments and demand both software and hardware optimization. Another limitation is that deep models are usually specialized into a single domain or task, requiring them to learn and store new parameters for each new one. Multi-Domain Learning (MDL) attempts to solve this problem by learning a single model that is capable of performing wel"},"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":"2210.08101","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T20:48:12Z","cross_cats_sorted":[],"title_canon_sha256":"3cb7ea7113216b61f4f1d72dd71f9a1b16c50d3fa092349b708faa0c8ff6bf44","abstract_canon_sha256":"760681ff75cfa05f4cd0d33d853930ab68834479e492e79d55961309945a4be0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:20.101844Z","signature_b64":"WqIDhT+YrZQ5YhMHL409BtWArAz9itJzeaBK63r3ylIegng02f1ol03Zu95OhbjIUzK9vCZ+RV5KgrP0/NaPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421ded878437e38ed1c7273d3659fa8e02d6500174ed9a1b4bebd821f8af3222","last_reissued_at":"2026-07-05T06:51:20.101328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:20.101328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Budget-Aware Pruning for Multi-Domain Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jurandy Almeida, Nicu Sebe, Rodrigo Berriel, Samuel Felipe dos Santos, Thiago Oliveira-Santos","submitted_at":"2022-10-14T20:48:12Z","abstract_excerpt":"Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such requirements hinder the use in resource-limited environments and demand both software and hardware optimization. Another limitation is that deep models are usually specialized into a single domain or task, requiring them to learn and store new parameters for each new one. Multi-Domain Learning (MDL) attempts to solve this problem by learning a single model that is capable of performing wel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08101","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/2210.08101/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":"2210.08101","created_at":"2026-07-05T06:51:20.101393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08101v3","created_at":"2026-07-05T06:51:20.101393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08101","created_at":"2026-07-05T06:51:20.101393+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIO63B4EG7RY","created_at":"2026-07-05T06:51:20.101393+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIO63B4EG7RY5UOH","created_at":"2026-07-05T06:51:20.101393+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIO63B4E","created_at":"2026-07-05T06:51:20.101393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY","json":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY.json","graph_json":"https://pith.science/api/pith-number/IIO63B4EG7RY5UOHE46TMWP2RY/graph.json","events_json":"https://pith.science/api/pith-number/IIO63B4EG7RY5UOHE46TMWP2RY/events.json","paper":"https://pith.science/paper/IIO63B4E"},"agent_actions":{"view_html":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY","download_json":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY.json","view_paper":"https://pith.science/paper/IIO63B4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08101&json=true","fetch_graph":"https://pith.science/api/pith-number/IIO63B4EG7RY5UOHE46TMWP2RY/graph.json","fetch_events":"https://pith.science/api/pith-number/IIO63B4EG7RY5UOHE46TMWP2RY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY/action/storage_attestation","attest_author":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY/action/author_attestation","sign_citation":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY/action/citation_signature","submit_replication":"https://pith.science/pith/IIO63B4EG7RY5UOHE46TMWP2RY/action/replication_record"}},"created_at":"2026-07-05T06:51:20.101393+00:00","updated_at":"2026-07-05T06:51:20.101393+00:00"}