{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TOFG5M2BK7JIY5AZSPRZZJO7VU","short_pith_number":"pith:TOFG5M2B","canonical_record":{"source":{"id":"2011.08382","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-17T02:39:19Z","cross_cats_sorted":[],"title_canon_sha256":"73efca07576937b04217cac90493cd6646fbaa24b9807082637f415ca1158ee3","abstract_canon_sha256":"21ac972297cda8dabc90a768d49f6b517fd47d0fa333dfb58d3930e6445b5a78"},"schema_version":"1.0"},"canonical_sha256":"9b8a6eb34157d28c741993e39ca5dfad06323947d885f1479124d82b365401af","source":{"kind":"arxiv","id":"2011.08382","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.08382","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"arxiv_version","alias_value":"2011.08382v4","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08382","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"pith_short_12","alias_value":"TOFG5M2BK7JI","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"pith_short_16","alias_value":"TOFG5M2BK7JIY5AZ","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"pith_short_8","alias_value":"TOFG5M2B","created_at":"2026-07-05T04:01:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TOFG5M2BK7JIY5AZSPRZZJO7VU","target":"record","payload":{"canonical_record":{"source":{"id":"2011.08382","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-17T02:39:19Z","cross_cats_sorted":[],"title_canon_sha256":"73efca07576937b04217cac90493cd6646fbaa24b9807082637f415ca1158ee3","abstract_canon_sha256":"21ac972297cda8dabc90a768d49f6b517fd47d0fa333dfb58d3930e6445b5a78"},"schema_version":"1.0"},"canonical_sha256":"9b8a6eb34157d28c741993e39ca5dfad06323947d885f1479124d82b365401af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:29.822660Z","signature_b64":"tlSLr1MdGHczdaa6UFUIUXZTYl9C1xcxGWd9uoOm4YOFjb/HPTox5tv6WydWeNp9IDPqU0T3gkzP/6owbQ1AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b8a6eb34157d28c741993e39ca5dfad06323947d885f1479124d82b365401af","last_reissued_at":"2026-07-05T04:01:29.822228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:29.822228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.08382","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:01:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChHbQ8wYPP+tYAWmETAwMJDMIRzPs1ZsS+GDUcpIhPf2EvoEjC7FY52ViQoFuDHimBaOdqMfeC9GFfgM75+0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:06:22.393876Z"},"content_sha256":"bffb6af190363ecf21c067ba1ac93ee624f5fcc6819a3f6e7abaa05ec61511a5","schema_version":"1.0","event_id":"sha256:bffb6af190363ecf21c067ba1ac93ee624f5fcc6819a3f6e7abaa05ec61511a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TOFG5M2BK7JIY5AZSPRZZJO7VU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Chao, Ling Shao, Mingbao Lin, Rongrong Ji, Shaojie Li, Yan Wang","submitted_at":"2020-11-17T02:39:19Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices. Prevalent methods for CNN compression cannot be directly applied to GANs due to the peculiarties of GAN tasks and the unstable adversarial training. To solve these, in this paper, we introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation. The former searches for a light-weight generator architecture in a training-adaptive manner. To overcome channel inconsistenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08382","kind":"arxiv","version":4},"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/2011.08382/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":"2026-07-05T04:01:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lT7GXb/Lh6rQNl14i5RTguiYLl8vrWW6R+VnIqGTZkpjYJaJNQ/Q6lyWgsPtTgx3AAjUjxd/44l5tCNEXQ42CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:06:22.394260Z"},"content_sha256":"e429c94b42b6b526e8a0fe4f3cc60c475b800eaa4b296857afcf318eb5b50604","schema_version":"1.0","event_id":"sha256:e429c94b42b6b526e8a0fe4f3cc60c475b800eaa4b296857afcf318eb5b50604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TOFG5M2BK7JIY5AZSPRZZJO7VU/bundle.json","state_url":"https://pith.science/pith/TOFG5M2BK7JIY5AZSPRZZJO7VU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TOFG5M2BK7JIY5AZSPRZZJO7VU/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":"2026-08-06T01:06:22Z","links":{"resolver":"https://pith.science/pith/TOFG5M2BK7JIY5AZSPRZZJO7VU","bundle":"https://pith.science/pith/TOFG5M2BK7JIY5AZSPRZZJO7VU/bundle.json","state":"https://pith.science/pith/TOFG5M2BK7JIY5AZSPRZZJO7VU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TOFG5M2BK7JIY5AZSPRZZJO7VU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TOFG5M2BK7JIY5AZSPRZZJO7VU","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":"21ac972297cda8dabc90a768d49f6b517fd47d0fa333dfb58d3930e6445b5a78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-17T02:39:19Z","title_canon_sha256":"73efca07576937b04217cac90493cd6646fbaa24b9807082637f415ca1158ee3"},"schema_version":"1.0","source":{"id":"2011.08382","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.08382","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"arxiv_version","alias_value":"2011.08382v4","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08382","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"pith_short_12","alias_value":"TOFG5M2BK7JI","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"pith_short_16","alias_value":"TOFG5M2BK7JIY5AZ","created_at":"2026-07-05T04:01:29Z"},{"alias_kind":"pith_short_8","alias_value":"TOFG5M2B","created_at":"2026-07-05T04:01:29Z"}],"graph_snapshots":[{"event_id":"sha256:e429c94b42b6b526e8a0fe4f3cc60c475b800eaa4b296857afcf318eb5b50604","target":"graph","created_at":"2026-07-05T04:01:29Z","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/2011.08382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices. Prevalent methods for CNN compression cannot be directly applied to GANs due to the peculiarties of GAN tasks and the unstable adversarial training. To solve these, in this paper, we introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation. The former searches for a light-weight generator architecture in a training-adaptive manner. To overcome channel inconsistenc","authors_text":"Fei Chao, Ling Shao, Mingbao Lin, Rongrong Ji, Shaojie Li, Yan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-17T02:39:19Z","title":"Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08382","kind":"arxiv","version":4},"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:bffb6af190363ecf21c067ba1ac93ee624f5fcc6819a3f6e7abaa05ec61511a5","target":"record","created_at":"2026-07-05T04:01:29Z","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":"21ac972297cda8dabc90a768d49f6b517fd47d0fa333dfb58d3930e6445b5a78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-17T02:39:19Z","title_canon_sha256":"73efca07576937b04217cac90493cd6646fbaa24b9807082637f415ca1158ee3"},"schema_version":"1.0","source":{"id":"2011.08382","kind":"arxiv","version":4}},"canonical_sha256":"9b8a6eb34157d28c741993e39ca5dfad06323947d885f1479124d82b365401af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b8a6eb34157d28c741993e39ca5dfad06323947d885f1479124d82b365401af","first_computed_at":"2026-07-05T04:01:29.822228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:29.822228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tlSLr1MdGHczdaa6UFUIUXZTYl9C1xcxGWd9uoOm4YOFjb/HPTox5tv6WydWeNp9IDPqU0T3gkzP/6owbQ1AAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:29.822660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.08382","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bffb6af190363ecf21c067ba1ac93ee624f5fcc6819a3f6e7abaa05ec61511a5","sha256:e429c94b42b6b526e8a0fe4f3cc60c475b800eaa4b296857afcf318eb5b50604"],"state_sha256":"3299d4d88706a5c15b1f2c180aa4f9c445c1f53e7aed4ddeda66ae3fc818593b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xitEO8JCGE0vdPy7wmMbbL+hAjr/gi3d6b9JRDlM6kOUffRYaj4yzogj5444AnoInRiQ+m3Vos6ui6za7RegCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:06:22.396850Z","bundle_sha256":"1f0b6cb18ce6aac67e2cfc7f922a11068dcb0e82cfc82ecac789fdd3e3153e40"}}