{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WAHLWGFBVVR6FER2ALD3EPJ3ZL","short_pith_number":"pith:WAHLWGFB","canonical_record":{"source":{"id":"2501.12115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T13:25:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ae3533de23104e503fdb1115dca38c1649630f9cbe64fec02216a61c25a13d2b","abstract_canon_sha256":"1371d42ffefe7085dba29d0b6acd96a2279eff891acdcd1933cb4e81122b7206"},"schema_version":"1.0"},"canonical_sha256":"b00ebb18a1ad63e2923a02c7b23d3bcaf6bbb5264438317ef6eb10796f31e326","source":{"kind":"arxiv","id":"2501.12115","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12115","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12115v1","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12115","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"WAHLWGFBVVR6","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"WAHLWGFBVVR6FER2","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"WAHLWGFB","created_at":"2026-07-05T10:03:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WAHLWGFBVVR6FER2ALD3EPJ3ZL","target":"record","payload":{"canonical_record":{"source":{"id":"2501.12115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T13:25:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ae3533de23104e503fdb1115dca38c1649630f9cbe64fec02216a61c25a13d2b","abstract_canon_sha256":"1371d42ffefe7085dba29d0b6acd96a2279eff891acdcd1933cb4e81122b7206"},"schema_version":"1.0"},"canonical_sha256":"b00ebb18a1ad63e2923a02c7b23d3bcaf6bbb5264438317ef6eb10796f31e326","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:31.691955Z","signature_b64":"6H6GslXLeJu0dn9jAVw4fJXpHTJRbtL+ITq26uLya0Fnb0MwG95kPLH0k9I8DmlLZ5K5bLYI0Bw8vAIwkacrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b00ebb18a1ad63e2923a02c7b23d3bcaf6bbb5264438317ef6eb10796f31e326","last_reissued_at":"2026-07-05T10:03:31.691551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:31.691551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.12115","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":"2026-07-05T10:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ms1HZTk5oZ62I6aDTuAoYzKomST8iCs4FspsLnhP2pXg7tnWVfeQyZz+DXUJBN2u0Nfx3wbrMrY/dRik0STQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:58:41.121214Z"},"content_sha256":"c7dc2563cff96d08a8da3bdea8a6ef309b754f0125071ae5d39b47c9eae2a45d","schema_version":"1.0","event_id":"sha256:c7dc2563cff96d08a8da3bdea8a6ef309b754f0125071ae5d39b47c9eae2a45d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WAHLWGFBVVR6FER2ALD3EPJ3ZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Marcus Liwicki, Rajkumar Saini, Richa Upadhyay, Ronald Phlypo","submitted_at":"2025-01-21T13:25:32Z","abstract_excerpt":"This paper presents meta-sparsity, a framework for learning model sparsity, basically learning the parameter that controls the degree of sparsity, that allows deep neural networks (DNNs) to inherently generate optimal sparse shared structures in multi-task learning (MTL) setting. This proposed approach enables the dynamic learning of sparsity patterns across a variety of tasks, unlike traditional sparsity methods that rely heavily on manual hyperparameter tuning. Inspired by Model Agnostic Meta-Learning (MAML), the emphasis is on learning shared and optimally sparse parameters in multi-task sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12115","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/2501.12115/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":"2026-07-05T10:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPV1HfNm3T/F5c4NDPDA65nZmxU/i3yt/awCuhC0IIfwDgzt4KwQl9ilkghSe5nH+PUDXy3yTpGWZIOipcLuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:58:41.121838Z"},"content_sha256":"0663e7e7136fac1688fc54bcba27005ab8d4e7243f205d87dc53c91b38d34346","schema_version":"1.0","event_id":"sha256:0663e7e7136fac1688fc54bcba27005ab8d4e7243f205d87dc53c91b38d34346"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAHLWGFBVVR6FER2ALD3EPJ3ZL/bundle.json","state_url":"https://pith.science/pith/WAHLWGFBVVR6FER2ALD3EPJ3ZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAHLWGFBVVR6FER2ALD3EPJ3ZL/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":"2026-07-09T05:58:41Z","links":{"resolver":"https://pith.science/pith/WAHLWGFBVVR6FER2ALD3EPJ3ZL","bundle":"https://pith.science/pith/WAHLWGFBVVR6FER2ALD3EPJ3ZL/bundle.json","state":"https://pith.science/pith/WAHLWGFBVVR6FER2ALD3EPJ3ZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAHLWGFBVVR6FER2ALD3EPJ3ZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WAHLWGFBVVR6FER2ALD3EPJ3ZL","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":"1371d42ffefe7085dba29d0b6acd96a2279eff891acdcd1933cb4e81122b7206","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T13:25:32Z","title_canon_sha256":"ae3533de23104e503fdb1115dca38c1649630f9cbe64fec02216a61c25a13d2b"},"schema_version":"1.0","source":{"id":"2501.12115","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12115","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12115v1","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12115","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"WAHLWGFBVVR6","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"WAHLWGFBVVR6FER2","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"WAHLWGFB","created_at":"2026-07-05T10:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:0663e7e7136fac1688fc54bcba27005ab8d4e7243f205d87dc53c91b38d34346","target":"graph","created_at":"2026-07-05T10:03:31Z","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/2501.12115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents meta-sparsity, a framework for learning model sparsity, basically learning the parameter that controls the degree of sparsity, that allows deep neural networks (DNNs) to inherently generate optimal sparse shared structures in multi-task learning (MTL) setting. This proposed approach enables the dynamic learning of sparsity patterns across a variety of tasks, unlike traditional sparsity methods that rely heavily on manual hyperparameter tuning. Inspired by Model Agnostic Meta-Learning (MAML), the emphasis is on learning shared and optimally sparse parameters in multi-task sc","authors_text":"Marcus Liwicki, Rajkumar Saini, Richa Upadhyay, Ronald Phlypo","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T13:25:32Z","title":"Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12115","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:c7dc2563cff96d08a8da3bdea8a6ef309b754f0125071ae5d39b47c9eae2a45d","target":"record","created_at":"2026-07-05T10:03:31Z","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":"1371d42ffefe7085dba29d0b6acd96a2279eff891acdcd1933cb4e81122b7206","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T13:25:32Z","title_canon_sha256":"ae3533de23104e503fdb1115dca38c1649630f9cbe64fec02216a61c25a13d2b"},"schema_version":"1.0","source":{"id":"2501.12115","kind":"arxiv","version":1}},"canonical_sha256":"b00ebb18a1ad63e2923a02c7b23d3bcaf6bbb5264438317ef6eb10796f31e326","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b00ebb18a1ad63e2923a02c7b23d3bcaf6bbb5264438317ef6eb10796f31e326","first_computed_at":"2026-07-05T10:03:31.691551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:31.691551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6H6GslXLeJu0dn9jAVw4fJXpHTJRbtL+ITq26uLya0Fnb0MwG95kPLH0k9I8DmlLZ5K5bLYI0Bw8vAIwkacrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:31.691955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12115","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7dc2563cff96d08a8da3bdea8a6ef309b754f0125071ae5d39b47c9eae2a45d","sha256:0663e7e7136fac1688fc54bcba27005ab8d4e7243f205d87dc53c91b38d34346"],"state_sha256":"188a63554b50fe55e305c4aefc2bd8bd350e4e01ab3ebcbaa9184d38fd0af671"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7v7wqAyeJSIX82qxJUf2GQvQhgtbj8wxu0tSh6SGVVbb0CbD/s+Bs1ms8dkexZmYufMu08iV8C515dqBbcwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:58:41.125627Z","bundle_sha256":"8af9bfb969d21b6bbd6b151a79b3fb797ddce6d33aaf13423f259fa2013a88b5"}}