{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:57Y2ZS33RZU3GYTW5NRLAPGY6Q","short_pith_number":"pith:57Y2ZS33","canonical_record":{"source":{"id":"1801.07365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T01:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"2334a986de3c49eb0676d1fac7cb22b6ad2681740dbc145cdd5fc37b10900c95","abstract_canon_sha256":"eab7f7cd116db9ec6b67c93c5421f2013e516db3c8bdc99c70e29d63dbbaf93e"},"schema_version":"1.0"},"canonical_sha256":"eff1accb7b8e69b36276eb62b03cd8f42b9c2b68eb099936d3e183632bb76433","source":{"kind":"arxiv","id":"1801.07365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07365","created_at":"2026-05-18T00:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07365v1","created_at":"2026-05-18T00:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07365","created_at":"2026-05-18T00:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"57Y2ZS33RZU3","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"57Y2ZS33RZU3GYTW","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"57Y2ZS33","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:57Y2ZS33RZU3GYTW5NRLAPGY6Q","target":"record","payload":{"canonical_record":{"source":{"id":"1801.07365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T01:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"2334a986de3c49eb0676d1fac7cb22b6ad2681740dbc145cdd5fc37b10900c95","abstract_canon_sha256":"eab7f7cd116db9ec6b67c93c5421f2013e516db3c8bdc99c70e29d63dbbaf93e"},"schema_version":"1.0"},"canonical_sha256":"eff1accb7b8e69b36276eb62b03cd8f42b9c2b68eb099936d3e183632bb76433","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:13.016275Z","signature_b64":"AQ9pO7AEmDOrHAW8P7titVbEV4IlJaYCp570Pu1bKO+0DL6+3KSWWSfYTrbUxj2rW+ydpN9LZYJO/HSXNFx7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eff1accb7b8e69b36276eb62b03cd8f42b9c2b68eb099936d3e183632bb76433","last_reissued_at":"2026-05-18T00:25:13.015827Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:13.015827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.07365","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":"2026-05-18T00:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5YvKJ4xz2Sh3ZFP9ftPV1JpY2Yv1RKX2OheREXjI48q6YvoEyQ/ayvNFfQR67qemfgIm6nOGepSjBYWD9ukWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:54:20.157674Z"},"content_sha256":"eccd2516abf7ebdc2ed7d6f8a59c8025e67d0b618de7eaec47e6edd1229296ad","schema_version":"1.0","event_id":"sha256:eccd2516abf7ebdc2ed7d6f8a59c8025e67d0b618de7eaec47e6edd1229296ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:57Y2ZS33RZU3GYTW5NRLAPGY6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Prune Filters in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Zhou, Qiangui Huang, Suya You, Ulrich Neumann","submitted_at":"2018-01-23T01:30:34Z","abstract_excerpt":"Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing resource consumptions. This paper presents a learning algorithm to simplify and speed up these CNNs. Specifically, we introduce a \"try-and-learn\" algorithm to train pruning agents that remove unnecessary CNN filters in a data-driven way. With the help of a novel reward function, our agents removes a significant number of filters in CNNs while maintaining perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07365","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":"2026-05-18T00:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8cF405T37TOBNN4JZHTl954x7iV83gCqVJ1dk7LUhMDnPDFtBwiCzC7+gHEBljM6KONdOt73OgpQSO3MkYXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:54:20.158017Z"},"content_sha256":"a63e02027c429879fe6566ec054a08fc5bcc47bfcdea5f2b22f71013a9b735ff","schema_version":"1.0","event_id":"sha256:a63e02027c429879fe6566ec054a08fc5bcc47bfcdea5f2b22f71013a9b735ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57Y2ZS33RZU3GYTW5NRLAPGY6Q/bundle.json","state_url":"https://pith.science/pith/57Y2ZS33RZU3GYTW5NRLAPGY6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57Y2ZS33RZU3GYTW5NRLAPGY6Q/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":"2026-06-08T21:54:20Z","links":{"resolver":"https://pith.science/pith/57Y2ZS33RZU3GYTW5NRLAPGY6Q","bundle":"https://pith.science/pith/57Y2ZS33RZU3GYTW5NRLAPGY6Q/bundle.json","state":"https://pith.science/pith/57Y2ZS33RZU3GYTW5NRLAPGY6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57Y2ZS33RZU3GYTW5NRLAPGY6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:57Y2ZS33RZU3GYTW5NRLAPGY6Q","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":"eab7f7cd116db9ec6b67c93c5421f2013e516db3c8bdc99c70e29d63dbbaf93e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T01:30:34Z","title_canon_sha256":"2334a986de3c49eb0676d1fac7cb22b6ad2681740dbc145cdd5fc37b10900c95"},"schema_version":"1.0","source":{"id":"1801.07365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07365","created_at":"2026-05-18T00:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07365v1","created_at":"2026-05-18T00:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07365","created_at":"2026-05-18T00:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"57Y2ZS33RZU3","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"57Y2ZS33RZU3GYTW","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"57Y2ZS33","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:a63e02027c429879fe6566ec054a08fc5bcc47bfcdea5f2b22f71013a9b735ff","target":"graph","created_at":"2026-05-18T00:25:13Z","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":"Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing resource consumptions. This paper presents a learning algorithm to simplify and speed up these CNNs. Specifically, we introduce a \"try-and-learn\" algorithm to train pruning agents that remove unnecessary CNN filters in a data-driven way. With the help of a novel reward function, our agents removes a significant number of filters in CNNs while maintaining perf","authors_text":"Kevin Zhou, Qiangui Huang, Suya You, Ulrich Neumann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T01:30:34Z","title":"Learning to Prune Filters in Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07365","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:eccd2516abf7ebdc2ed7d6f8a59c8025e67d0b618de7eaec47e6edd1229296ad","target":"record","created_at":"2026-05-18T00:25:13Z","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":"eab7f7cd116db9ec6b67c93c5421f2013e516db3c8bdc99c70e29d63dbbaf93e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T01:30:34Z","title_canon_sha256":"2334a986de3c49eb0676d1fac7cb22b6ad2681740dbc145cdd5fc37b10900c95"},"schema_version":"1.0","source":{"id":"1801.07365","kind":"arxiv","version":1}},"canonical_sha256":"eff1accb7b8e69b36276eb62b03cd8f42b9c2b68eb099936d3e183632bb76433","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eff1accb7b8e69b36276eb62b03cd8f42b9c2b68eb099936d3e183632bb76433","first_computed_at":"2026-05-18T00:25:13.015827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:13.015827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AQ9pO7AEmDOrHAW8P7titVbEV4IlJaYCp570Pu1bKO+0DL6+3KSWWSfYTrbUxj2rW+ydpN9LZYJO/HSXNFx7Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:13.016275Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.07365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eccd2516abf7ebdc2ed7d6f8a59c8025e67d0b618de7eaec47e6edd1229296ad","sha256:a63e02027c429879fe6566ec054a08fc5bcc47bfcdea5f2b22f71013a9b735ff"],"state_sha256":"10e2e295da7e329525f83c631ce093b907c7dd89b9edd52eb820d9c02b1bab69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAskV81eOqngA42yM7agE2KuLna2NoF4914rqnChoZ4F0OusmWsWoNRMQ0LtYsOXn1QfX4tmz1qHu8ffEoi7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T21:54:20.159885Z","bundle_sha256":"8cdb78569e5cf7e23d716a6b79ba01b8144e92d88307b9ade2b4ee856b85b06d"}}