{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2ZDSV2G52IYRDTG7AV5HMCK7SU","short_pith_number":"pith:2ZDSV2G5","canonical_record":{"source":{"id":"1805.08941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-23T03:05:48Z","cross_cats_sorted":[],"title_canon_sha256":"6f58ae497413f4fc9068079c5abddcdd666ed6d8d972f9e7cab1e700c59ddfcd","abstract_canon_sha256":"24df164446bac2eee0b80220954a8e443fb3b81cb03fbcd6429a07277db26db8"},"schema_version":"1.0"},"canonical_sha256":"d6472ae8ddd23111ccdf057a76095f950ba5d8fd91fa9ea927568ce5ec7dafad","source":{"kind":"arxiv","id":"1805.08941","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08941","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08941v3","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08941","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"pith_short_12","alias_value":"2ZDSV2G52IYR","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2ZDSV2G52IYRDTG7","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2ZDSV2G5","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2ZDSV2G52IYRDTG7AV5HMCK7SU","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-23T03:05:48Z","cross_cats_sorted":[],"title_canon_sha256":"6f58ae497413f4fc9068079c5abddcdd666ed6d8d972f9e7cab1e700c59ddfcd","abstract_canon_sha256":"24df164446bac2eee0b80220954a8e443fb3b81cb03fbcd6429a07277db26db8"},"schema_version":"1.0"},"canonical_sha256":"d6472ae8ddd23111ccdf057a76095f950ba5d8fd91fa9ea927568ce5ec7dafad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:10.027192Z","signature_b64":"AzZP1nvxDrZEuA78mhqSP088aP07qX6rZE2yWE1pAxpcsn1Ddb7BNSlNUl2m6JXfAvKx6GUvkft9Zaba7CsFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6472ae8ddd23111ccdf057a76095f950ba5d8fd91fa9ea927568ce5ec7dafad","last_reissued_at":"2026-05-17T23:56:10.026527Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:10.026527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08941","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":"2026-05-17T23:56:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MiPVPnF++ULrrHV30gHaeD8R4qKpJaeeRYqR5iHWb1EteiywZH5Pg3d+zUKVA3UxjlTDFrynVexVmh6fwzGPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:23:19.484674Z"},"content_sha256":"f88e1b6afe8bbb66c440014962ae13d08998165a2ca7913b0bb945f2be270fbd","schema_version":"1.0","event_id":"sha256:f88e1b6afe8bbb66c440014962ae13d08998165a2ca7913b0bb945f2be270fbd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2ZDSV2G52IYRDTG7AV5HMCK7SU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian-Hao Luo, Jianxin Wu","submitted_at":"2018-05-23T03:05:48Z","abstract_excerpt":"Channel pruning is an important family of methods to speed up deep model's inference. Previous filter pruning algorithms regard channel pruning and model fine-tuning as two independent steps. This paper argues that combining them into a single end-to-end trainable system will lead to better results. We propose an efficient channel selection layer, namely AutoPruner, to find less important filters automatically in a joint training manner. Our AutoPruner takes previous activation responses as an input and generates a true binary index code for pruning. Hence, all the filters corresponding to zer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08941","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":""},"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":"2026-05-17T23:56:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wo1b+2uh6AZecX5EhoiDXRB1jqipjo7hsp1mxfs52Tz/sqDZk5XYzUd0MY+acYfJnWcKbSjlJAIQNzJwLHgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:23:19.485143Z"},"content_sha256":"b52561fc1a1aba743764d7718c8a0618159aabf3fe868b06c238abe46bff45db","schema_version":"1.0","event_id":"sha256:b52561fc1a1aba743764d7718c8a0618159aabf3fe868b06c238abe46bff45db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZDSV2G52IYRDTG7AV5HMCK7SU/bundle.json","state_url":"https://pith.science/pith/2ZDSV2G52IYRDTG7AV5HMCK7SU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZDSV2G52IYRDTG7AV5HMCK7SU/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":"2026-05-23T12:23:19Z","links":{"resolver":"https://pith.science/pith/2ZDSV2G52IYRDTG7AV5HMCK7SU","bundle":"https://pith.science/pith/2ZDSV2G52IYRDTG7AV5HMCK7SU/bundle.json","state":"https://pith.science/pith/2ZDSV2G52IYRDTG7AV5HMCK7SU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZDSV2G52IYRDTG7AV5HMCK7SU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2ZDSV2G52IYRDTG7AV5HMCK7SU","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":"24df164446bac2eee0b80220954a8e443fb3b81cb03fbcd6429a07277db26db8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-23T03:05:48Z","title_canon_sha256":"6f58ae497413f4fc9068079c5abddcdd666ed6d8d972f9e7cab1e700c59ddfcd"},"schema_version":"1.0","source":{"id":"1805.08941","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08941","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08941v3","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08941","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"pith_short_12","alias_value":"2ZDSV2G52IYR","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2ZDSV2G52IYRDTG7","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2ZDSV2G5","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:b52561fc1a1aba743764d7718c8a0618159aabf3fe868b06c238abe46bff45db","target":"graph","created_at":"2026-05-17T23:56:10Z","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":"Channel pruning is an important family of methods to speed up deep model's inference. Previous filter pruning algorithms regard channel pruning and model fine-tuning as two independent steps. This paper argues that combining them into a single end-to-end trainable system will lead to better results. We propose an efficient channel selection layer, namely AutoPruner, to find less important filters automatically in a joint training manner. Our AutoPruner takes previous activation responses as an input and generates a true binary index code for pruning. Hence, all the filters corresponding to zer","authors_text":"Jian-Hao Luo, Jianxin Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-23T03:05:48Z","title":"AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08941","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:f88e1b6afe8bbb66c440014962ae13d08998165a2ca7913b0bb945f2be270fbd","target":"record","created_at":"2026-05-17T23:56:10Z","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":"24df164446bac2eee0b80220954a8e443fb3b81cb03fbcd6429a07277db26db8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-23T03:05:48Z","title_canon_sha256":"6f58ae497413f4fc9068079c5abddcdd666ed6d8d972f9e7cab1e700c59ddfcd"},"schema_version":"1.0","source":{"id":"1805.08941","kind":"arxiv","version":3}},"canonical_sha256":"d6472ae8ddd23111ccdf057a76095f950ba5d8fd91fa9ea927568ce5ec7dafad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6472ae8ddd23111ccdf057a76095f950ba5d8fd91fa9ea927568ce5ec7dafad","first_computed_at":"2026-05-17T23:56:10.026527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:10.026527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AzZP1nvxDrZEuA78mhqSP088aP07qX6rZE2yWE1pAxpcsn1Ddb7BNSlNUl2m6JXfAvKx6GUvkft9Zaba7CsFDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:10.027192Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08941","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f88e1b6afe8bbb66c440014962ae13d08998165a2ca7913b0bb945f2be270fbd","sha256:b52561fc1a1aba743764d7718c8a0618159aabf3fe868b06c238abe46bff45db"],"state_sha256":"b3c832a5946868eb9cbcf2b6f2cb8e68851935713e894cd912ee56ad5025a5f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aOdL3ev5/GhCW9QhErNY259ikIVrnnEe6aj6WlbsD2Y92jherTP2gSuFFoXiSzTcPJx35sNmGWI1gG5gWMR6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T12:23:19.488097Z","bundle_sha256":"3b1e0daa6b0bb7ea46d69adea144a08f455382d3fa0240bb0729cfa41e572457"}}