{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IW26GK7AKZ77SPPG5F7I77SS64","short_pith_number":"pith:IW26GK7A","schema_version":"1.0","canonical_sha256":"45b5e32be0567ff93de6e97e8ffe52f7399e9d4dbef95b7c2765dfadeaf99419","source":{"kind":"arxiv","id":"1907.07171","version":4},"attestation_state":"computed","paper":{"title":"On the \"steerability\" of generative adversarial networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Jahanian, Lucy Chai, Phillip Isola","submitted_at":"2019-07-16T17:55:07Z","abstract_excerpt":"An open secret in contemporary machine learning is that many models work beautifully on standard benchmarks but fail to generalize outside the lab. This has been attributed to biased training data, which provide poor coverage over real world events. Generative models are no exception, but recent advances in generative adversarial networks (GANs) suggest otherwise - these models can now synthesize strikingly realistic and diverse images. Is generative modeling of photos a solved problem? We show that although current GANs can fit standard datasets very well, they still fall short of being compr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1907.07171","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-16T17:55:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e753eaacb28494d0c71847ddc94a3445dfaa339f3016c0e0aae7d302b9b8a44f","abstract_canon_sha256":"efc60738ac8036fb38ed211798f0d9cd65a4367f39bf82c85a943ee7d15cbffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:57.016966Z","signature_b64":"yfeOK4Kqj7kvxaS11ep06i9NiZnl5+Rtb6oW3ONa4dSngjyXmPvylBwqEBOPx+cxlijlnoZv0JEctViVmwwnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b5e32be0567ff93de6e97e8ffe52f7399e9d4dbef95b7c2765dfadeaf99419","last_reissued_at":"2026-07-05T00:40:57.016521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:57.016521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the \"steerability\" of generative adversarial networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Jahanian, Lucy Chai, Phillip Isola","submitted_at":"2019-07-16T17:55:07Z","abstract_excerpt":"An open secret in contemporary machine learning is that many models work beautifully on standard benchmarks but fail to generalize outside the lab. This has been attributed to biased training data, which provide poor coverage over real world events. Generative models are no exception, but recent advances in generative adversarial networks (GANs) suggest otherwise - these models can now synthesize strikingly realistic and diverse images. Is generative modeling of photos a solved problem? We show that although current GANs can fit standard datasets very well, they still fall short of being compr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07171","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/1907.07171/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.07171","created_at":"2026-07-05T00:40:57.016578+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.07171v4","created_at":"2026-07-05T00:40:57.016578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07171","created_at":"2026-07-05T00:40:57.016578+00:00"},{"alias_kind":"pith_short_12","alias_value":"IW26GK7AKZ77","created_at":"2026-07-05T00:40:57.016578+00:00"},{"alias_kind":"pith_short_16","alias_value":"IW26GK7AKZ77SPPG","created_at":"2026-07-05T00:40:57.016578+00:00"},{"alias_kind":"pith_short_8","alias_value":"IW26GK7A","created_at":"2026-07-05T00:40:57.016578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29358","citing_title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2405.07987","citing_title":"The Platonic Representation Hypothesis","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64","json":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64.json","graph_json":"https://pith.science/api/pith-number/IW26GK7AKZ77SPPG5F7I77SS64/graph.json","events_json":"https://pith.science/api/pith-number/IW26GK7AKZ77SPPG5F7I77SS64/events.json","paper":"https://pith.science/paper/IW26GK7A"},"agent_actions":{"view_html":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64","download_json":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64.json","view_paper":"https://pith.science/paper/IW26GK7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.07171&json=true","fetch_graph":"https://pith.science/api/pith-number/IW26GK7AKZ77SPPG5F7I77SS64/graph.json","fetch_events":"https://pith.science/api/pith-number/IW26GK7AKZ77SPPG5F7I77SS64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64/action/storage_attestation","attest_author":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64/action/author_attestation","sign_citation":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64/action/citation_signature","submit_replication":"https://pith.science/pith/IW26GK7AKZ77SPPG5F7I77SS64/action/replication_record"}},"created_at":"2026-07-05T00:40:57.016578+00:00","updated_at":"2026-07-05T00:40:57.016578+00:00"}