{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:472BV26ZZWDWPA6DRJAONCP6WG","short_pith_number":"pith:472BV26Z","canonical_record":{"source":{"id":"1903.11728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T23:17:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"171a72a928a4717cf04558f1b0c51a27c1cad3b3276ee7f1f8606fc6ef4e4c88","abstract_canon_sha256":"6ac42f7e9f24dc81011d8b781cab47ad927f661d959a5a18546e3c95349be8ba"},"schema_version":"1.0"},"canonical_sha256":"e7f41aebd9cd876783c38a40e689feb1a8eb928641be2321686074f44530ab62","source":{"kind":"arxiv","id":"1903.11728","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.11728","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"arxiv_version","alias_value":"1903.11728v2","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11728","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"pith_short_12","alias_value":"472BV26ZZWDW","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"472BV26ZZWDWPA6D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"472BV26Z","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:472BV26ZZWDWPA6DRJAONCP6WG","target":"record","payload":{"canonical_record":{"source":{"id":"1903.11728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T23:17:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"171a72a928a4717cf04558f1b0c51a27c1cad3b3276ee7f1f8606fc6ef4e4c88","abstract_canon_sha256":"6ac42f7e9f24dc81011d8b781cab47ad927f661d959a5a18546e3c95349be8ba"},"schema_version":"1.0"},"canonical_sha256":"e7f41aebd9cd876783c38a40e689feb1a8eb928641be2321686074f44530ab62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.874974Z","signature_b64":"oirb6tC+4Vg3znNXQwqGHWGYi5yg9AA0dflLD+3HfpIjcmDq+aqTvUh3NiagvkQM3m0uauA86IV1QfkHhYWyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f41aebd9cd876783c38a40e689feb1a8eb928641be2321686074f44530ab62","last_reissued_at":"2026-05-17T23:44:28.874506Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.874506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.11728","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ooT/UA9jrbsgo18+BENSrA/7tQhwBSGSp048dNjlLacZVAENNm+H8X1Gm4ifVpxQuMdTig7mvtcM7rQJjLa8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:53:23.474961Z"},"content_sha256":"eafd483e6d7fcd161bd193c4197ff88e0ac36124f83fa02cd816e49a4721978e","schema_version":"1.0","event_id":"sha256:eafd483e6d7fcd161bd193c4197ff88e0ac36124f83fa02cd816e49a4721978e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:472BV26ZZWDWPA6DRJAONCP6WG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoSlim: Towards One-Shot Architecture Search for Channel Numbers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahui Yu, Thomas Huang","submitted_at":"2019-03-27T23:17:28Z","abstract_excerpt":"We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and one-shot solution, named AutoSlim, is presented. Instead of training many network samples and searching with reinforcement learning, we train a single slimmable network to approximate the network accuracy of different channel configurations. We then iteratively evaluate the trained slimmable model and greedily slim the layer with minimal accuracy drop. By this single pass, we can obtain the optimized channel configur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11728","kind":"arxiv","version":2},"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":"2026-05-17T23:44:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BCOH+gKRIyz5Sq1WMlVXPE+aA47g46Gp91nnDdwOwnB8oMWtVOncIEVmeVN7N9PNDWFV+NqfwRlpKX3kZtMgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:53:23.475509Z"},"content_sha256":"c7dd0eddad9d5ba955385ac768ad8301e767a98abbbdf00248e6b841940f8cbf","schema_version":"1.0","event_id":"sha256:c7dd0eddad9d5ba955385ac768ad8301e767a98abbbdf00248e6b841940f8cbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/472BV26ZZWDWPA6DRJAONCP6WG/bundle.json","state_url":"https://pith.science/pith/472BV26ZZWDWPA6DRJAONCP6WG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/472BV26ZZWDWPA6DRJAONCP6WG/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":"2026-05-31T10:53:23Z","links":{"resolver":"https://pith.science/pith/472BV26ZZWDWPA6DRJAONCP6WG","bundle":"https://pith.science/pith/472BV26ZZWDWPA6DRJAONCP6WG/bundle.json","state":"https://pith.science/pith/472BV26ZZWDWPA6DRJAONCP6WG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/472BV26ZZWDWPA6DRJAONCP6WG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:472BV26ZZWDWPA6DRJAONCP6WG","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":"6ac42f7e9f24dc81011d8b781cab47ad927f661d959a5a18546e3c95349be8ba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T23:17:28Z","title_canon_sha256":"171a72a928a4717cf04558f1b0c51a27c1cad3b3276ee7f1f8606fc6ef4e4c88"},"schema_version":"1.0","source":{"id":"1903.11728","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.11728","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"arxiv_version","alias_value":"1903.11728v2","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11728","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"pith_short_12","alias_value":"472BV26ZZWDW","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"472BV26ZZWDWPA6D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"472BV26Z","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:c7dd0eddad9d5ba955385ac768ad8301e767a98abbbdf00248e6b841940f8cbf","target":"graph","created_at":"2026-05-17T23:44:28Z","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":"We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and one-shot solution, named AutoSlim, is presented. Instead of training many network samples and searching with reinforcement learning, we train a single slimmable network to approximate the network accuracy of different channel configurations. We then iteratively evaluate the trained slimmable model and greedily slim the layer with minimal accuracy drop. By this single pass, we can obtain the optimized channel configur","authors_text":"Jiahui Yu, Thomas Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T23:17:28Z","title":"AutoSlim: Towards One-Shot Architecture Search for Channel Numbers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11728","kind":"arxiv","version":2},"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:eafd483e6d7fcd161bd193c4197ff88e0ac36124f83fa02cd816e49a4721978e","target":"record","created_at":"2026-05-17T23:44:28Z","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":"6ac42f7e9f24dc81011d8b781cab47ad927f661d959a5a18546e3c95349be8ba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T23:17:28Z","title_canon_sha256":"171a72a928a4717cf04558f1b0c51a27c1cad3b3276ee7f1f8606fc6ef4e4c88"},"schema_version":"1.0","source":{"id":"1903.11728","kind":"arxiv","version":2}},"canonical_sha256":"e7f41aebd9cd876783c38a40e689feb1a8eb928641be2321686074f44530ab62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7f41aebd9cd876783c38a40e689feb1a8eb928641be2321686074f44530ab62","first_computed_at":"2026-05-17T23:44:28.874506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:28.874506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oirb6tC+4Vg3znNXQwqGHWGYi5yg9AA0dflLD+3HfpIjcmDq+aqTvUh3NiagvkQM3m0uauA86IV1QfkHhYWyBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:28.874974Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.11728","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eafd483e6d7fcd161bd193c4197ff88e0ac36124f83fa02cd816e49a4721978e","sha256:c7dd0eddad9d5ba955385ac768ad8301e767a98abbbdf00248e6b841940f8cbf"],"state_sha256":"9316301171ac5d1cc72b19ce400925e6e1be348f88435c911b8ca192a8dc6e0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"43ncuKZFxFnjma3WoHx+v1rEotYUhEpXlAjtRE6WAys+Oy5SCMWereMxmbWJ53zKdghXFuz1Ozd7e/3SAYGNAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T10:53:23.479143Z","bundle_sha256":"66c564a07c9eff602ee1525ce6925e351dc2b90d71a6510498d8cab83f1248de"}}