{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EG2ANQYCJDCE7MF2UTSBX6UWIQ","short_pith_number":"pith:EG2ANQYC","canonical_record":{"source":{"id":"2308.12114","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T13:09:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"598c0cb34777b6e86aa8d0b42f0cde0999c3603361d66009b851b1a4b928e687","abstract_canon_sha256":"94a2826fee4eb667212e50aca82a22c93b559084015accd27a89b03a025864de"},"schema_version":"1.0"},"canonical_sha256":"21b406c30248c44fb0baa4e41bfa9644144cce5af578dd39c0f314a84e12467c","source":{"kind":"arxiv","id":"2308.12114","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12114","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12114v3","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12114","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"pith_short_12","alias_value":"EG2ANQYCJDCE","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"pith_short_16","alias_value":"EG2ANQYCJDCE7MF2","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"pith_short_8","alias_value":"EG2ANQYC","created_at":"2026-07-05T07:18:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EG2ANQYCJDCE7MF2UTSBX6UWIQ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.12114","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T13:09:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"598c0cb34777b6e86aa8d0b42f0cde0999c3603361d66009b851b1a4b928e687","abstract_canon_sha256":"94a2826fee4eb667212e50aca82a22c93b559084015accd27a89b03a025864de"},"schema_version":"1.0"},"canonical_sha256":"21b406c30248c44fb0baa4e41bfa9644144cce5af578dd39c0f314a84e12467c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:29.020833Z","signature_b64":"9FlEC2MK/dks1CaIiOFQwHEmnP3jgWYBTqpIkMhLvQuTDign2/MSH2E0a+FK31earcuhK0zfXz3waL1fwrS2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21b406c30248c44fb0baa4e41bfa9644144cce5af578dd39c0f314a84e12467c","last_reissued_at":"2026-07-05T07:18:29.020323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:29.020323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.12114","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":"2026-07-05T07:18:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GKNkhb2E9r6m7vJwR4GU/NVr9pzMpGfyp30Jbw6nMasso0gAfvnqFe3i9WhxOSZ38wR3bAYaztWeIv9nklm9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:02:54.675951Z"},"content_sha256":"1925fe597c45ed11c29e912715614ae345103df83ed978eb12a8cb762d59e6e1","schema_version":"1.0","event_id":"sha256:1925fe597c45ed11c29e912715614ae345103df83ed978eb12a8cb762d59e6e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EG2ANQYCJDCE7MF2UTSBX6UWIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less is More -- Towards parsimonious multi-task models using structured sparsity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Marcus Liwicki, Rajkumar Saini, Richa Upadhyay, Ronald Phlypo","submitted_at":"2023-08-23T13:09:03Z","abstract_excerpt":"Model sparsification in deep learning promotes simpler, more interpretable models with fewer parameters. This not only reduces the model's memory footprint and computational needs but also shortens inference time. This work focuses on creating sparse models optimized for multiple tasks with fewer parameters. These parsimonious models also possess the potential to match or outperform dense models in terms of performance. In this work, we introduce channel-wise l1/l2 group sparsity in the shared convolutional layers parameters (or weights) of the multi-task learning model. This approach facilita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12114","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/2308.12114/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":"2026-07-05T07:18:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+gxcs18EN9NsOzBrdetNpZLhMUzcUyTIl54yPjphUY2/l0fISluAWEGjer8Hr4hWbXOAFvGuVHxRfHgvEOl8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:02:54.676588Z"},"content_sha256":"4a15a5079444a7ccc92e1513cbf6c8e536486a382cc0061b0a4789f7d8afdded","schema_version":"1.0","event_id":"sha256:4a15a5079444a7ccc92e1513cbf6c8e536486a382cc0061b0a4789f7d8afdded"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EG2ANQYCJDCE7MF2UTSBX6UWIQ/bundle.json","state_url":"https://pith.science/pith/EG2ANQYCJDCE7MF2UTSBX6UWIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EG2ANQYCJDCE7MF2UTSBX6UWIQ/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":"2026-07-09T06:02:54Z","links":{"resolver":"https://pith.science/pith/EG2ANQYCJDCE7MF2UTSBX6UWIQ","bundle":"https://pith.science/pith/EG2ANQYCJDCE7MF2UTSBX6UWIQ/bundle.json","state":"https://pith.science/pith/EG2ANQYCJDCE7MF2UTSBX6UWIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EG2ANQYCJDCE7MF2UTSBX6UWIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EG2ANQYCJDCE7MF2UTSBX6UWIQ","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":"94a2826fee4eb667212e50aca82a22c93b559084015accd27a89b03a025864de","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T13:09:03Z","title_canon_sha256":"598c0cb34777b6e86aa8d0b42f0cde0999c3603361d66009b851b1a4b928e687"},"schema_version":"1.0","source":{"id":"2308.12114","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12114","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12114v3","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12114","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"pith_short_12","alias_value":"EG2ANQYCJDCE","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"pith_short_16","alias_value":"EG2ANQYCJDCE7MF2","created_at":"2026-07-05T07:18:29Z"},{"alias_kind":"pith_short_8","alias_value":"EG2ANQYC","created_at":"2026-07-05T07:18:29Z"}],"graph_snapshots":[{"event_id":"sha256:4a15a5079444a7ccc92e1513cbf6c8e536486a382cc0061b0a4789f7d8afdded","target":"graph","created_at":"2026-07-05T07:18:29Z","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/2308.12114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model sparsification in deep learning promotes simpler, more interpretable models with fewer parameters. This not only reduces the model's memory footprint and computational needs but also shortens inference time. This work focuses on creating sparse models optimized for multiple tasks with fewer parameters. These parsimonious models also possess the potential to match or outperform dense models in terms of performance. In this work, we introduce channel-wise l1/l2 group sparsity in the shared convolutional layers parameters (or weights) of the multi-task learning model. This approach facilita","authors_text":"Marcus Liwicki, Rajkumar Saini, Richa Upadhyay, Ronald Phlypo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T13:09:03Z","title":"Less is More -- Towards parsimonious multi-task models using structured sparsity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12114","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":"sha256:1925fe597c45ed11c29e912715614ae345103df83ed978eb12a8cb762d59e6e1","target":"record","created_at":"2026-07-05T07:18:29Z","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":"94a2826fee4eb667212e50aca82a22c93b559084015accd27a89b03a025864de","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T13:09:03Z","title_canon_sha256":"598c0cb34777b6e86aa8d0b42f0cde0999c3603361d66009b851b1a4b928e687"},"schema_version":"1.0","source":{"id":"2308.12114","kind":"arxiv","version":3}},"canonical_sha256":"21b406c30248c44fb0baa4e41bfa9644144cce5af578dd39c0f314a84e12467c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21b406c30248c44fb0baa4e41bfa9644144cce5af578dd39c0f314a84e12467c","first_computed_at":"2026-07-05T07:18:29.020323Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:29.020323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9FlEC2MK/dks1CaIiOFQwHEmnP3jgWYBTqpIkMhLvQuTDign2/MSH2E0a+FK31earcuhK0zfXz3waL1fwrS2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:29.020833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12114","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1925fe597c45ed11c29e912715614ae345103df83ed978eb12a8cb762d59e6e1","sha256:4a15a5079444a7ccc92e1513cbf6c8e536486a382cc0061b0a4789f7d8afdded"],"state_sha256":"35aaee709a166c60f484741463d07a3b3e65b7e4f1d38826df4d922feca2f20f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MU1X/RTnalF0jL0r7ugG36Jme1UYc+1TWnSz+vhtB3r10Xe33XBMqOFs9g9uWKNn3DTQoDaNRS+ayTvqNiUaCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:02:54.679066Z","bundle_sha256":"d8f0ee5187482ecd59c414465d7d1fc669bbd7ae5540baf04a5993cb32472c05"}}