{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2HKZPAZZR6K32Y3EN2QJAGFWSV","short_pith_number":"pith:2HKZPAZZ","canonical_record":{"source":{"id":"2112.09130","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:59:50Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"f460a0fc6034f6fb6e03a567767dcefbaf989353136ee994a1b646a910b48a4f","abstract_canon_sha256":"5b7e7acd0fa88049137449a715d512a7b2f9f5f67d349540c0521f755a3e87e2"},"schema_version":"1.0"},"canonical_sha256":"d1d59783398f95bd63646ea09018b6956fd622931ffbac2333283a69a6cf8e42","source":{"kind":"arxiv","id":"2112.09130","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.09130","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2112.09130v3","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09130","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"2HKZPAZZR6K3","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"2HKZPAZZR6K32Y3E","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"2HKZPAZZ","created_at":"2026-07-05T04:20:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2HKZPAZZR6K32Y3EN2QJAGFWSV","target":"record","payload":{"canonical_record":{"source":{"id":"2112.09130","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:59:50Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"f460a0fc6034f6fb6e03a567767dcefbaf989353136ee994a1b646a910b48a4f","abstract_canon_sha256":"5b7e7acd0fa88049137449a715d512a7b2f9f5f67d349540c0521f755a3e87e2"},"schema_version":"1.0"},"canonical_sha256":"d1d59783398f95bd63646ea09018b6956fd622931ffbac2333283a69a6cf8e42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:17.576823Z","signature_b64":"rHlSJg8VM/PqLJbHtrsdX1S7Uqb3gku6Smd8ds/MznhFtNn3IsfA+IeR0fJve6vJr2cepf+0RE6eWSugU2lgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1d59783398f95bd63646ea09018b6956fd622931ffbac2333283a69a6cf8e42","last_reissued_at":"2026-07-05T04:20:17.576341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:17.576341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.09130","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":"2026-07-05T04:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tC3b11KQ4nvRvmo59zIh/3tUbb8czOQuPK1Gq57o7unvbDTmUEcVdOj6Mr/pGYsIS7xpoX/XS3Ha/DReQm6+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:29:25.821127Z"},"content_sha256":"2b2235ff9467d2a4854da72fa47fa2fdee74ede0b116fdcccd84f27f65b480d7","schema_version":"1.0","event_id":"sha256:2b2235ff9467d2a4854da72fa47fa2fdee74ede0b116fdcccd84f27f65b480d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2HKZPAZZR6K32Y3EN2QJAGFWSV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensembling Off-the-shelf Models for GAN Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eli Shechtman, Jun-Yan Zhu, Nupur Kumari, Richard Zhang","submitted_at":"2021-12-16T18:59:50Z","abstract_excerpt":"The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from scratch in an unsupervised manner. Can the collective \"knowledge\" from a large bank of pretrained vision models be leveraged to improve GAN training? If so, with so many models to choose from, which one(s) should be selected, and in what manner are they most effective? We find that pretrained computer vision models can significantly improve performance when used in an ensemble of discriminators. Notably, the particula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09130","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.09130/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":"2026-07-05T04:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5LQ42HOUUcJrc8DnZwFBPZT1gNemNJfFyrGHUvGy9ueRlOz67nbu0B7ghQYaa40Q3hsmuhbjDU8S8d3DwB6WCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:29:25.821814Z"},"content_sha256":"9de00bca2f9ad470470058bf361221347e60ea5defc4ad38ea2272b97360c454","schema_version":"1.0","event_id":"sha256:9de00bca2f9ad470470058bf361221347e60ea5defc4ad38ea2272b97360c454"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2HKZPAZZR6K32Y3EN2QJAGFWSV/bundle.json","state_url":"https://pith.science/pith/2HKZPAZZR6K32Y3EN2QJAGFWSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2HKZPAZZR6K32Y3EN2QJAGFWSV/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":"2026-08-04T19:29:25Z","links":{"resolver":"https://pith.science/pith/2HKZPAZZR6K32Y3EN2QJAGFWSV","bundle":"https://pith.science/pith/2HKZPAZZR6K32Y3EN2QJAGFWSV/bundle.json","state":"https://pith.science/pith/2HKZPAZZR6K32Y3EN2QJAGFWSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2HKZPAZZR6K32Y3EN2QJAGFWSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2HKZPAZZR6K32Y3EN2QJAGFWSV","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":"5b7e7acd0fa88049137449a715d512a7b2f9f5f67d349540c0521f755a3e87e2","cross_cats_sorted":["cs.GR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:59:50Z","title_canon_sha256":"f460a0fc6034f6fb6e03a567767dcefbaf989353136ee994a1b646a910b48a4f"},"schema_version":"1.0","source":{"id":"2112.09130","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.09130","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2112.09130v3","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09130","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"2HKZPAZZR6K3","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"2HKZPAZZR6K32Y3E","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"2HKZPAZZ","created_at":"2026-07-05T04:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:9de00bca2f9ad470470058bf361221347e60ea5defc4ad38ea2272b97360c454","target":"graph","created_at":"2026-07-05T04:20:17Z","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/2112.09130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from scratch in an unsupervised manner. Can the collective \"knowledge\" from a large bank of pretrained vision models be leveraged to improve GAN training? If so, with so many models to choose from, which one(s) should be selected, and in what manner are they most effective? We find that pretrained computer vision models can significantly improve performance when used in an ensemble of discriminators. Notably, the particula","authors_text":"Eli Shechtman, Jun-Yan Zhu, Nupur Kumari, Richard Zhang","cross_cats":["cs.GR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:59:50Z","title":"Ensembling Off-the-shelf Models for GAN Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09130","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":"sha256:2b2235ff9467d2a4854da72fa47fa2fdee74ede0b116fdcccd84f27f65b480d7","target":"record","created_at":"2026-07-05T04:20:17Z","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":"5b7e7acd0fa88049137449a715d512a7b2f9f5f67d349540c0521f755a3e87e2","cross_cats_sorted":["cs.GR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T18:59:50Z","title_canon_sha256":"f460a0fc6034f6fb6e03a567767dcefbaf989353136ee994a1b646a910b48a4f"},"schema_version":"1.0","source":{"id":"2112.09130","kind":"arxiv","version":3}},"canonical_sha256":"d1d59783398f95bd63646ea09018b6956fd622931ffbac2333283a69a6cf8e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1d59783398f95bd63646ea09018b6956fd622931ffbac2333283a69a6cf8e42","first_computed_at":"2026-07-05T04:20:17.576341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:17.576341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rHlSJg8VM/PqLJbHtrsdX1S7Uqb3gku6Smd8ds/MznhFtNn3IsfA+IeR0fJve6vJr2cepf+0RE6eWSugU2lgCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:17.576823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.09130","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b2235ff9467d2a4854da72fa47fa2fdee74ede0b116fdcccd84f27f65b480d7","sha256:9de00bca2f9ad470470058bf361221347e60ea5defc4ad38ea2272b97360c454"],"state_sha256":"3edd82371a783fb831c475a8190a47504cd1e09b9d91b98fd9a0899284398af9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CI0kH/w6oXwcZ+E+ZpbeCyuwSD478REVwRmo3QkNQXxbYydhGFYKakU0zAJfojwzxnDioC/7OfMPbl/l6Dc3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:29:25.826300Z","bundle_sha256":"c34b336ddd2e4ad56c54873ecaa0a68d411caa93c550374df0d2d7bf516e4563"}}