{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6EHFORIPCIQO5ZYNLJIUXBRH4C","short_pith_number":"pith:6EHFORIP","canonical_record":{"source":{"id":"1801.09335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T01:16:03Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"add638cf15411724951daae19c425a6f5660d1938cf83f4f6526c58e2e16f468","abstract_canon_sha256":"796bdd7836ab9294ded8c1e6ba0656160670671ee334a3ff245b9ad936abc157"},"schema_version":"1.0"},"canonical_sha256":"f10e57450f1220eee70d5a514b8627e09e437c7a04ba9198f3f747f15ff59337","source":{"kind":"arxiv","id":"1801.09335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09335","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09335v1","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09335","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"6EHFORIPCIQO","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6EHFORIPCIQO5ZYN","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6EHFORIP","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6EHFORIPCIQO5ZYNLJIUXBRH4C","target":"record","payload":{"canonical_record":{"source":{"id":"1801.09335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T01:16:03Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"add638cf15411724951daae19c425a6f5660d1938cf83f4f6526c58e2e16f468","abstract_canon_sha256":"796bdd7836ab9294ded8c1e6ba0656160670671ee334a3ff245b9ad936abc157"},"schema_version":"1.0"},"canonical_sha256":"f10e57450f1220eee70d5a514b8627e09e437c7a04ba9198f3f747f15ff59337","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:57.771077Z","signature_b64":"sp9tUiauqaUHgUvinvTC+mqsjPDp/fA8SwqKUQ3kPL6qJcY8ZV6Kv3eVUu/0t0Tv4DbKSkxGu22+2K92CSZFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f10e57450f1220eee70d5a514b8627e09e437c7a04ba9198f3f747f15ff59337","last_reissued_at":"2026-05-18T00:24:57.770492Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:57.770492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.09335","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":"2026-05-18T00:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ccAs1xTZAA+KFVm+oDjdJvOm89QQzLszrbzjHW+zby4frHd3YZK4SbsBO5DTYFb8JavS1a3DmJSOLPyRRHn7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:42:26.929224Z"},"content_sha256":"cd14fe4467b8902124d9494b5fedc3f9eed77bb4fd323a6164ed1338c6f10fb4","schema_version":"1.0","event_id":"sha256:cd14fe4467b8902124d9494b5fedc3f9eed77bb4fd323a6164ed1338c6f10fb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6EHFORIPCIQO5ZYNLJIUXBRH4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Gang Wang, Jason Kuen, Jianxiong Yin, Simon See, Xiangfei Kong, Yap-Peng Tan, Zhe Lin","submitted_at":"2018-01-29T01:16:03Z","abstract_excerpt":"It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent on the changing real-time resource availability. Thus, it is inadequate to train just inference-efficient CNNs, whose inference costs are not adjustable and cannot adapt to varied inference budgets. We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint). During training, SDPoint applies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09335","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":"2026-05-18T00:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5LhpLCIvVYLxPLYePmGWVoarcnVVDQzalvpLt7ESOvWNMywNZIrM3HE7fzJsikXMuK37ZR0IMWoBWj/OCXgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:42:26.929748Z"},"content_sha256":"4d49efb4e18c3b48be42466f6e24d9e8398017d7cc65468b96745acc84ccbe24","schema_version":"1.0","event_id":"sha256:4d49efb4e18c3b48be42466f6e24d9e8398017d7cc65468b96745acc84ccbe24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EHFORIPCIQO5ZYNLJIUXBRH4C/bundle.json","state_url":"https://pith.science/pith/6EHFORIPCIQO5ZYNLJIUXBRH4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EHFORIPCIQO5ZYNLJIUXBRH4C/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":"2026-05-26T21:42:26Z","links":{"resolver":"https://pith.science/pith/6EHFORIPCIQO5ZYNLJIUXBRH4C","bundle":"https://pith.science/pith/6EHFORIPCIQO5ZYNLJIUXBRH4C/bundle.json","state":"https://pith.science/pith/6EHFORIPCIQO5ZYNLJIUXBRH4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EHFORIPCIQO5ZYNLJIUXBRH4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6EHFORIPCIQO5ZYNLJIUXBRH4C","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":"796bdd7836ab9294ded8c1e6ba0656160670671ee334a3ff245b9ad936abc157","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T01:16:03Z","title_canon_sha256":"add638cf15411724951daae19c425a6f5660d1938cf83f4f6526c58e2e16f468"},"schema_version":"1.0","source":{"id":"1801.09335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09335","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09335v1","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09335","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"6EHFORIPCIQO","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6EHFORIPCIQO5ZYN","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6EHFORIP","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:4d49efb4e18c3b48be42466f6e24d9e8398017d7cc65468b96745acc84ccbe24","target":"graph","created_at":"2026-05-18T00:24:57Z","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":"It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent on the changing real-time resource availability. Thus, it is inadequate to train just inference-efficient CNNs, whose inference costs are not adjustable and cannot adapt to varied inference budgets. We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint). During training, SDPoint applies","authors_text":"Gang Wang, Jason Kuen, Jianxiong Yin, Simon See, Xiangfei Kong, Yap-Peng Tan, Zhe Lin","cross_cats":["cs.CV","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T01:16:03Z","title":"Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09335","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:cd14fe4467b8902124d9494b5fedc3f9eed77bb4fd323a6164ed1338c6f10fb4","target":"record","created_at":"2026-05-18T00:24:57Z","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":"796bdd7836ab9294ded8c1e6ba0656160670671ee334a3ff245b9ad936abc157","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T01:16:03Z","title_canon_sha256":"add638cf15411724951daae19c425a6f5660d1938cf83f4f6526c58e2e16f468"},"schema_version":"1.0","source":{"id":"1801.09335","kind":"arxiv","version":1}},"canonical_sha256":"f10e57450f1220eee70d5a514b8627e09e437c7a04ba9198f3f747f15ff59337","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f10e57450f1220eee70d5a514b8627e09e437c7a04ba9198f3f747f15ff59337","first_computed_at":"2026-05-18T00:24:57.770492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:57.770492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sp9tUiauqaUHgUvinvTC+mqsjPDp/fA8SwqKUQ3kPL6qJcY8ZV6Kv3eVUu/0t0Tv4DbKSkxGu22+2K92CSZFAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:57.771077Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.09335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd14fe4467b8902124d9494b5fedc3f9eed77bb4fd323a6164ed1338c6f10fb4","sha256:4d49efb4e18c3b48be42466f6e24d9e8398017d7cc65468b96745acc84ccbe24"],"state_sha256":"36096f1028a5bdb87c394b041807009c57aefaeb4aab9bf903d76b5cb3cd7498"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+mIL6IFK0VmRzTSl4TCTggMhkBTCyOsfQ8jID440OUVhCZk4aEBkwtuWzLq/3Tb5AAq/8//cdQE6oSHoKhxsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T21:42:26.934398Z","bundle_sha256":"5dcccfcfe8392c6714ea0632d7742f5fffc0b1ae24f61274391869e30487730d"}}