{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RRB3LDHCAJVNUMFP62HNQJJR6L","short_pith_number":"pith:RRB3LDHC","schema_version":"1.0","canonical_sha256":"8c43b58ce2026ada30aff68ed82531f2ffb9a3ef2c2c43aa8757eb9bb7ec8254","source":{"kind":"arxiv","id":"2507.01722","version":3},"attestation_state":"computed","paper":{"title":"When Does Pruning Benefit Vision Representations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Bragagnolo, Enrico Cassano, Marco Grangetto, Riccardo Renzulli","submitted_at":"2025-07-02T13:57:49Z","abstract_excerpt":"Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper investigates how pruning influences vision models across three key dimensions: (i) interpretability, (ii) unsupervised object discovery, and (iii) alignment with human perception. We first analyze different vision network architectures to examine how varying sparsity levels affect feature attribution interpretability methods. Additionally, we explore whether pruning promotes more succinct and structured representations, po"},"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":"2507.01722","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T13:57:49Z","cross_cats_sorted":[],"title_canon_sha256":"0adcb0981f68b2dafada6b871cd2816be86d6ae6d39118d6f86ca608cc85f97f","abstract_canon_sha256":"707a6b37d91d97316fe464c63670a3d61c8b00d525b335c11bc28eaa221e4742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:25.866736Z","signature_b64":"PJdNONptX9s10Gbi0pMA0QEM/iFjfNc3D5tqSB2Vr0PFMzeNQ5yfHTXBJW02q/iG6TGsVqIMmIy+kJfgWHE0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c43b58ce2026ada30aff68ed82531f2ffb9a3ef2c2c43aa8757eb9bb7ec8254","last_reissued_at":"2026-07-05T11:33:25.866236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:25.866236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Does Pruning Benefit Vision Representations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Bragagnolo, Enrico Cassano, Marco Grangetto, Riccardo Renzulli","submitted_at":"2025-07-02T13:57:49Z","abstract_excerpt":"Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper investigates how pruning influences vision models across three key dimensions: (i) interpretability, (ii) unsupervised object discovery, and (iii) alignment with human perception. We first analyze different vision network architectures to examine how varying sparsity levels affect feature attribution interpretability methods. Additionally, we explore whether pruning promotes more succinct and structured representations, po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01722","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/2507.01722/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":"2507.01722","created_at":"2026-07-05T11:33:25.866304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01722v3","created_at":"2026-07-05T11:33:25.866304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01722","created_at":"2026-07-05T11:33:25.866304+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRB3LDHCAJVN","created_at":"2026-07-05T11:33:25.866304+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRB3LDHCAJVNUMFP","created_at":"2026-07-05T11:33:25.866304+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRB3LDHC","created_at":"2026-07-05T11:33:25.866304+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/RRB3LDHCAJVNUMFP62HNQJJR6L","json":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L.json","graph_json":"https://pith.science/api/pith-number/RRB3LDHCAJVNUMFP62HNQJJR6L/graph.json","events_json":"https://pith.science/api/pith-number/RRB3LDHCAJVNUMFP62HNQJJR6L/events.json","paper":"https://pith.science/paper/RRB3LDHC"},"agent_actions":{"view_html":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L","download_json":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L.json","view_paper":"https://pith.science/paper/RRB3LDHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01722&json=true","fetch_graph":"https://pith.science/api/pith-number/RRB3LDHCAJVNUMFP62HNQJJR6L/graph.json","fetch_events":"https://pith.science/api/pith-number/RRB3LDHCAJVNUMFP62HNQJJR6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/action/storage_attestation","attest_author":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/action/author_attestation","sign_citation":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/action/citation_signature","submit_replication":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/action/replication_record"}},"created_at":"2026-07-05T11:33:25.866304+00:00","updated_at":"2026-07-05T11:33:25.866304+00:00"}