{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OCR6STEUBPTLN5IGFRESFYAA2I","short_pith_number":"pith:OCR6STEU","canonical_record":{"source":{"id":"1905.04446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-11T04:37:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d2ca6888afdbc01a1015c199fa8cd9bf84efbc8c18cc7f462ba5c4130faf05c3","abstract_canon_sha256":"4c4c8f42a68278a95552a8c597c6635aaa69ef8a61f5563fcf78bfaefce3487b"},"schema_version":"1.0"},"canonical_sha256":"70a3e94c940be6b6f5062c4922e000d22e4d0108bcf6282539af11f2b6386273","source":{"kind":"arxiv","id":"1905.04446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04446","created_at":"2026-05-17T23:46:24Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04446v1","created_at":"2026-05-17T23:46:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04446","created_at":"2026-05-17T23:46:24Z"},{"alias_kind":"pith_short_12","alias_value":"OCR6STEUBPTL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OCR6STEUBPTLN5IG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OCR6STEU","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OCR6STEUBPTLN5IGFRESFYAA2I","target":"record","payload":{"canonical_record":{"source":{"id":"1905.04446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-11T04:37:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d2ca6888afdbc01a1015c199fa8cd9bf84efbc8c18cc7f462ba5c4130faf05c3","abstract_canon_sha256":"4c4c8f42a68278a95552a8c597c6635aaa69ef8a61f5563fcf78bfaefce3487b"},"schema_version":"1.0"},"canonical_sha256":"70a3e94c940be6b6f5062c4922e000d22e4d0108bcf6282539af11f2b6386273","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:24.827555Z","signature_b64":"xTRmbYSFn1DkhFsprUqIFetUaXufT1C3hpZoQLKDpJHWIdjWB+8SgFx2haHSypSVZTxMCnS6B4qVPTfbjmRTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a3e94c940be6b6f5062c4922e000d22e4d0108bcf6282539af11f2b6386273","last_reissued_at":"2026-05-17T23:46:24.826922Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:24.826922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.04446","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":"2026-05-17T23:46:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3S/qsOYWNXuij+ynu4DobnMzA6g+zyuLDA+yXM/eD8Gj/xeS0sxa9UKDJksYIRyIMrPDzR3yMkfqn+nGbJryDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T07:33:38.576051Z"},"content_sha256":"a4f962d518bef5eee083d0640be213331a9f16dfd39080f0b496d2f533ea41ba","schema_version":"1.0","event_id":"sha256:a4f962d518bef5eee083d0640be213331a9f16dfd39080f0b496d2f533ea41ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OCR6STEUBPTLN5IGFRESFYAA2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Play and Prune: Adaptive Filter Pruning for Deep Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Piyush Rai, Pravendra Singh, Vinay Kumar Verma, Vinay P. Namboodiri","submitted_at":"2019-05-11T04:37:10Z","abstract_excerpt":"While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as computational overheads. Consequently, there is a growing need for filter-level pruning approaches for compressing CNN based models that not only reduce the total number of parameters but reduce the overall computation as well. We present a new min-max framework for filter-level pruning of CNNs. Our framework, called Play and Prune (PP), jointly prunes and f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04446","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":""},"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":"2026-05-17T23:46:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKzjDzmTe1gUEfOVgJCE93fr43QF1fpVjsDVmyS6e6rvpQrlctQxKmbDRfdCaJwhbAc5xEB13LgIEe2s/IhSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T07:33:38.576419Z"},"content_sha256":"8f0c62286c2dbac088549f3eeae917a791527918056d198f93fd7a4d0389af72","schema_version":"1.0","event_id":"sha256:8f0c62286c2dbac088549f3eeae917a791527918056d198f93fd7a4d0389af72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCR6STEUBPTLN5IGFRESFYAA2I/bundle.json","state_url":"https://pith.science/pith/OCR6STEUBPTLN5IGFRESFYAA2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCR6STEUBPTLN5IGFRESFYAA2I/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":"2026-05-20T07:33:38Z","links":{"resolver":"https://pith.science/pith/OCR6STEUBPTLN5IGFRESFYAA2I","bundle":"https://pith.science/pith/OCR6STEUBPTLN5IGFRESFYAA2I/bundle.json","state":"https://pith.science/pith/OCR6STEUBPTLN5IGFRESFYAA2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCR6STEUBPTLN5IGFRESFYAA2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OCR6STEUBPTLN5IGFRESFYAA2I","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":"4c4c8f42a68278a95552a8c597c6635aaa69ef8a61f5563fcf78bfaefce3487b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-11T04:37:10Z","title_canon_sha256":"d2ca6888afdbc01a1015c199fa8cd9bf84efbc8c18cc7f462ba5c4130faf05c3"},"schema_version":"1.0","source":{"id":"1905.04446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04446","created_at":"2026-05-17T23:46:24Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04446v1","created_at":"2026-05-17T23:46:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04446","created_at":"2026-05-17T23:46:24Z"},{"alias_kind":"pith_short_12","alias_value":"OCR6STEUBPTL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OCR6STEUBPTLN5IG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OCR6STEU","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:8f0c62286c2dbac088549f3eeae917a791527918056d198f93fd7a4d0389af72","target":"graph","created_at":"2026-05-17T23:46:24Z","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"},"paper":{"abstract_excerpt":"While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as computational overheads. Consequently, there is a growing need for filter-level pruning approaches for compressing CNN based models that not only reduce the total number of parameters but reduce the overall computation as well. We present a new min-max framework for filter-level pruning of CNNs. Our framework, called Play and Prune (PP), jointly prunes and f","authors_text":"Piyush Rai, Pravendra Singh, Vinay Kumar Verma, Vinay P. Namboodiri","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-11T04:37:10Z","title":"Play and Prune: Adaptive Filter Pruning for Deep Model Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04446","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:a4f962d518bef5eee083d0640be213331a9f16dfd39080f0b496d2f533ea41ba","target":"record","created_at":"2026-05-17T23:46:24Z","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":"4c4c8f42a68278a95552a8c597c6635aaa69ef8a61f5563fcf78bfaefce3487b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-11T04:37:10Z","title_canon_sha256":"d2ca6888afdbc01a1015c199fa8cd9bf84efbc8c18cc7f462ba5c4130faf05c3"},"schema_version":"1.0","source":{"id":"1905.04446","kind":"arxiv","version":1}},"canonical_sha256":"70a3e94c940be6b6f5062c4922e000d22e4d0108bcf6282539af11f2b6386273","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70a3e94c940be6b6f5062c4922e000d22e4d0108bcf6282539af11f2b6386273","first_computed_at":"2026-05-17T23:46:24.826922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:24.826922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xTRmbYSFn1DkhFsprUqIFetUaXufT1C3hpZoQLKDpJHWIdjWB+8SgFx2haHSypSVZTxMCnS6B4qVPTfbjmRTAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:24.827555Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.04446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4f962d518bef5eee083d0640be213331a9f16dfd39080f0b496d2f533ea41ba","sha256:8f0c62286c2dbac088549f3eeae917a791527918056d198f93fd7a4d0389af72"],"state_sha256":"e00057a02e30fa7a4ccaa82f9d2388fca0473940464faffa97b5bd059b4cafda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3ZJv+DyathpnsRQg5GqoNHsri2+qkgWLRipVy0QUh9tDTAdCzs3tpLQfblUb4qsXqTFTLYjLgh0gs3Lyt6uAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T07:33:38.578334Z","bundle_sha256":"b99769884045ab86dcb48511e1018ab3dc00088f87a8231e28f826b482e72a04"}}