{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RRB3LDHCAJVNUMFP62HNQJJR6L","short_pith_number":"pith:RRB3LDHC","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"},"canonical_sha256":"8c43b58ce2026ada30aff68ed82531f2ffb9a3ef2c2c43aa8757eb9bb7ec8254","source":{"kind":"arxiv","id":"2507.01722","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01722","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01722v3","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01722","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"RRB3LDHCAJVN","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_16","alias_value":"RRB3LDHCAJVNUMFP","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_8","alias_value":"RRB3LDHC","created_at":"2026-07-05T11:33:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RRB3LDHCAJVNUMFP62HNQJJR6L","target":"record","payload":{"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"},"canonical_sha256":"8c43b58ce2026ada30aff68ed82531f2ffb9a3ef2c2c43aa8757eb9bb7ec8254","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"},"source_kind":"arxiv","source_id":"2507.01722","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":"2026-07-05T11:33:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeJZvqKFQblx0rg5OVwWCmLD9EenSuh9QrzfEWI83Z+Hw2Ug73WfhGo8nawnfgekljJxsbmHMRCs4ofsva97BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:12:34.186146Z"},"content_sha256":"6fa1bf63297ea20be08094facc923b47b89af155d07eb3e734c4053b8df6f52b","schema_version":"1.0","event_id":"sha256:6fa1bf63297ea20be08094facc923b47b89af155d07eb3e734c4053b8df6f52b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RRB3LDHCAJVNUMFP62HNQJJR6L","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TJJNXFbQAAZiJmgJo9lcMre1Dm7cAjWEUlIJGdhTMgq4X2pMgZQu1masHAwgQwmWAciAbmj6OwA87ryeRt+5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:12:34.186637Z"},"content_sha256":"dff715d35343ccdfc6dff66dfebcb69f359f545ba9ea154423780c688a032aa8","schema_version":"1.0","event_id":"sha256:dff715d35343ccdfc6dff66dfebcb69f359f545ba9ea154423780c688a032aa8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/bundle.json","state_url":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/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":"2026-08-07T06:12:34Z","links":{"resolver":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L","bundle":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/bundle.json","state":"https://pith.science/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRB3LDHCAJVNUMFP62HNQJJR6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RRB3LDHCAJVNUMFP62HNQJJR6L","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":"707a6b37d91d97316fe464c63670a3d61c8b00d525b335c11bc28eaa221e4742","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T13:57:49Z","title_canon_sha256":"0adcb0981f68b2dafada6b871cd2816be86d6ae6d39118d6f86ca608cc85f97f"},"schema_version":"1.0","source":{"id":"2507.01722","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01722","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01722v3","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01722","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"RRB3LDHCAJVN","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_16","alias_value":"RRB3LDHCAJVNUMFP","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_8","alias_value":"RRB3LDHC","created_at":"2026-07-05T11:33:25Z"}],"graph_snapshots":[{"event_id":"sha256:dff715d35343ccdfc6dff66dfebcb69f359f545ba9ea154423780c688a032aa8","target":"graph","created_at":"2026-07-05T11:33:25Z","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/2507.01722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrea Bragagnolo, Enrico Cassano, Marco Grangetto, Riccardo Renzulli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T13:57:49Z","title":"When Does Pruning Benefit Vision Representations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01722","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":"sha256:6fa1bf63297ea20be08094facc923b47b89af155d07eb3e734c4053b8df6f52b","target":"record","created_at":"2026-07-05T11:33:25Z","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":"707a6b37d91d97316fe464c63670a3d61c8b00d525b335c11bc28eaa221e4742","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T13:57:49Z","title_canon_sha256":"0adcb0981f68b2dafada6b871cd2816be86d6ae6d39118d6f86ca608cc85f97f"},"schema_version":"1.0","source":{"id":"2507.01722","kind":"arxiv","version":3}},"canonical_sha256":"8c43b58ce2026ada30aff68ed82531f2ffb9a3ef2c2c43aa8757eb9bb7ec8254","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c43b58ce2026ada30aff68ed82531f2ffb9a3ef2c2c43aa8757eb9bb7ec8254","first_computed_at":"2026-07-05T11:33:25.866236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:25.866236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PJdNONptX9s10Gbi0pMA0QEM/iFjfNc3D5tqSB2Vr0PFMzeNQ5yfHTXBJW02q/iG6TGsVqIMmIy+kJfgWHE0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:25.866736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01722","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fa1bf63297ea20be08094facc923b47b89af155d07eb3e734c4053b8df6f52b","sha256:dff715d35343ccdfc6dff66dfebcb69f359f545ba9ea154423780c688a032aa8"],"state_sha256":"27d0a4c16db13c1d5fef48407bed969e0e1a7bb45f595abd519e2d9d02eeda1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2lx3X4l8sos/sd8g3DF2MJYJ9t8ZzT2Ex79PqKmHOzz0WvqDjW25+qaCdZRsbNqV/jjTfdA6EDjKtmKs3FRADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:12:34.191596Z","bundle_sha256":"5a5804e8d3292ff1df3be02108a9bcf098d4dd0abc36671685bced399696df52"}}