{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IJRRCKRFLVKPLSXFE4MCJO4QZ4","short_pith_number":"pith:IJRRCKRF","canonical_record":{"source":{"id":"2007.04756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-09T13:06:07Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"00039974de1da356a7d6547ac1ff6a20d5b090e1f2526a15cde4038a5508bf1a","abstract_canon_sha256":"58c043179c64af7857773028cc0cf883596e4108a81b23c1d3db90c328a87c9c"},"schema_version":"1.0"},"canonical_sha256":"4263112a255d54f5cae5271824bb90cf066146f2e8af9b51f0d8813e0e0373dd","source":{"kind":"arxiv","id":"2007.04756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.04756","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2007.04756v1","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04756","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"IJRRCKRFLVKP","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"IJRRCKRFLVKPLSXF","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"IJRRCKRF","created_at":"2026-07-05T01:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IJRRCKRFLVKPLSXFE4MCJO4QZ4","target":"record","payload":{"canonical_record":{"source":{"id":"2007.04756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-09T13:06:07Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"00039974de1da356a7d6547ac1ff6a20d5b090e1f2526a15cde4038a5508bf1a","abstract_canon_sha256":"58c043179c64af7857773028cc0cf883596e4108a81b23c1d3db90c328a87c9c"},"schema_version":"1.0"},"canonical_sha256":"4263112a255d54f5cae5271824bb90cf066146f2e8af9b51f0d8813e0e0373dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:08.513833Z","signature_b64":"TtqaZB5gm4MJC6ZhUJiFNwcCdq8JnXe2895g1ZGW/YbKINkuyiK0N0u9iVSmOxf3zW6dnRI/s82436GsZicVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4263112a255d54f5cae5271824bb90cf066146f2e8af9b51f0d8813e0e0373dd","last_reissued_at":"2026-07-05T01:21:08.513233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:08.513233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.04756","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":"2026-07-05T01:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LgKUfJHo58iWqUFI+qt9xVdRnqm5UnkuBNnodC5npJ1GT/3s6V0v3RREBgHntpyKBkc4bwU1QMCa15JRVJm2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:09:37.773960Z"},"content_sha256":"2b14da8c30e6c091e378df6facc27d6c4a78e4761265fd3a793a8d457ac47d26","schema_version":"1.0","event_id":"sha256:2b14da8c30e6c091e378df6facc27d6c4a78e4761265fd3a793a8d457ac47d26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IJRRCKRFLVKPLSXFE4MCJO4QZ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Prune Deep Neural Networks via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Aleksandra Kalisz, Lin Jie, Manas Gupta, Siddharth Aravindan, Vijay Chandrasekhar","submitted_at":"2020-07-09T13:06:07Z","abstract_excerpt":"This paper proposes PuRL - a deep reinforcement learning (RL) based algorithm for pruning neural networks. Unlike current RL based model compression approaches where feedback is given only at the end of each episode to the agent, PuRL provides rewards at every pruning step. This enables PuRL to achieve sparsity and accuracy comparable to current state-of-the-art methods, while having a much shorter training cycle. PuRL achieves more than 80% sparsity on the ResNet-50 model while retaining a Top-1 accuracy of 75.37% on the ImageNet dataset. Through our experiments we show that PuRL is also able"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04756","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/2007.04756/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":"2026-07-05T01:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WnNZsqrSZ6aPGlin8rvP+IHSG2wvM9kPFi2fB0ydV443U1EkF72F+S/6xnmm4Xz5f0RdRICTPKoFr8SaFWulCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:09:37.774536Z"},"content_sha256":"2633ce0f2517333d858ad727d863a39005362198f82f097683d4b92630e9d851","schema_version":"1.0","event_id":"sha256:2633ce0f2517333d858ad727d863a39005362198f82f097683d4b92630e9d851"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJRRCKRFLVKPLSXFE4MCJO4QZ4/bundle.json","state_url":"https://pith.science/pith/IJRRCKRFLVKPLSXFE4MCJO4QZ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJRRCKRFLVKPLSXFE4MCJO4QZ4/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":"2026-08-03T17:09:37Z","links":{"resolver":"https://pith.science/pith/IJRRCKRFLVKPLSXFE4MCJO4QZ4","bundle":"https://pith.science/pith/IJRRCKRFLVKPLSXFE4MCJO4QZ4/bundle.json","state":"https://pith.science/pith/IJRRCKRFLVKPLSXFE4MCJO4QZ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJRRCKRFLVKPLSXFE4MCJO4QZ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IJRRCKRFLVKPLSXFE4MCJO4QZ4","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":"58c043179c64af7857773028cc0cf883596e4108a81b23c1d3db90c328a87c9c","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-09T13:06:07Z","title_canon_sha256":"00039974de1da356a7d6547ac1ff6a20d5b090e1f2526a15cde4038a5508bf1a"},"schema_version":"1.0","source":{"id":"2007.04756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.04756","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2007.04756v1","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04756","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"IJRRCKRFLVKP","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"IJRRCKRFLVKPLSXF","created_at":"2026-07-05T01:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"IJRRCKRF","created_at":"2026-07-05T01:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:2633ce0f2517333d858ad727d863a39005362198f82f097683d4b92630e9d851","target":"graph","created_at":"2026-07-05T01:21:08Z","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/2007.04756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes PuRL - a deep reinforcement learning (RL) based algorithm for pruning neural networks. Unlike current RL based model compression approaches where feedback is given only at the end of each episode to the agent, PuRL provides rewards at every pruning step. This enables PuRL to achieve sparsity and accuracy comparable to current state-of-the-art methods, while having a much shorter training cycle. PuRL achieves more than 80% sparsity on the ResNet-50 model while retaining a Top-1 accuracy of 75.37% on the ImageNet dataset. Through our experiments we show that PuRL is also able","authors_text":"Aleksandra Kalisz, Lin Jie, Manas Gupta, Siddharth Aravindan, Vijay Chandrasekhar","cross_cats":["cs.CV","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-09T13:06:07Z","title":"Learning to Prune Deep Neural Networks via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04756","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":"sha256:2b14da8c30e6c091e378df6facc27d6c4a78e4761265fd3a793a8d457ac47d26","target":"record","created_at":"2026-07-05T01:21:08Z","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":"58c043179c64af7857773028cc0cf883596e4108a81b23c1d3db90c328a87c9c","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-09T13:06:07Z","title_canon_sha256":"00039974de1da356a7d6547ac1ff6a20d5b090e1f2526a15cde4038a5508bf1a"},"schema_version":"1.0","source":{"id":"2007.04756","kind":"arxiv","version":1}},"canonical_sha256":"4263112a255d54f5cae5271824bb90cf066146f2e8af9b51f0d8813e0e0373dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4263112a255d54f5cae5271824bb90cf066146f2e8af9b51f0d8813e0e0373dd","first_computed_at":"2026-07-05T01:21:08.513233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:21:08.513233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TtqaZB5gm4MJC6ZhUJiFNwcCdq8JnXe2895g1ZGW/YbKINkuyiK0N0u9iVSmOxf3zW6dnRI/s82436GsZicVCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:21:08.513833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.04756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b14da8c30e6c091e378df6facc27d6c4a78e4761265fd3a793a8d457ac47d26","sha256:2633ce0f2517333d858ad727d863a39005362198f82f097683d4b92630e9d851"],"state_sha256":"50b33c8aa76b6bbe6e1f16a5d6f32e14ea26a2e24019b550bd3c98870e1a5260"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KidiYF5OhPB3KDQhgMdZzyTgOsIabTENZvFNBgUE7EciAPrkrraxdzhQbwB5mLqsnGrLDLrNqM2NOuzuYJywAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:09:37.778383Z","bundle_sha256":"2937c0f9cd138d812c4989f20541c721819621e78321d162c41ef2008ed50102"}}