{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:32BUO7JCVPMPEBIHCKWGBXHK5Y","short_pith_number":"pith:32BUO7JC","canonical_record":{"source":{"id":"1810.12686","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T11:58:16Z","cross_cats_sorted":[],"title_canon_sha256":"55383921803f63e0573cf0dfa68d4bc6660ecb965accb68f64d406fab4b16767","abstract_canon_sha256":"4e1509fe33c1f44ec18ab49656b4eaac556cc431e586ad87ce86e5c403450b1b"},"schema_version":"1.0"},"canonical_sha256":"de83477d22abd8f2050712ac60dceaee25ae13ae2f49dce0915d8907467548d9","source":{"kind":"arxiv","id":"1810.12686","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12686","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12686v2","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12686","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"32BUO7JCVPMP","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"32BUO7JCVPMPEBIH","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"32BUO7JC","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:32BUO7JCVPMPEBIHCKWGBXHK5Y","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12686","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T11:58:16Z","cross_cats_sorted":[],"title_canon_sha256":"55383921803f63e0573cf0dfa68d4bc6660ecb965accb68f64d406fab4b16767","abstract_canon_sha256":"4e1509fe33c1f44ec18ab49656b4eaac556cc431e586ad87ce86e5c403450b1b"},"schema_version":"1.0"},"canonical_sha256":"de83477d22abd8f2050712ac60dceaee25ae13ae2f49dce0915d8907467548d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:38.399482Z","signature_b64":"7yDA9csxNu19GECwnUijdgeI1YODfagFigT+qo5fHolVc8aS98kiPQYRpfKRCXfNxdgER8d2GV42/6VaNVN6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de83477d22abd8f2050712ac60dceaee25ae13ae2f49dce0915d8907467548d9","last_reissued_at":"2026-05-17T23:50:38.398974Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:38.398974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12686","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":"2026-05-17T23:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTFCSmoXEQpMg99f5LCygpLmnCyOL6ojx/iy/wAisbDpsU0IJgszpOCE/G601t6Z8K1ewFKssV06SQAztk/UBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:49:11.114191Z"},"content_sha256":"d6a51c8deb88e5e27830f4b3347da0beea6e54647bd12dee6bba994e60ef242a","schema_version":"1.0","event_id":"sha256:d6a51c8deb88e5e27830f4b3347da0beea6e54647bd12dee6bba994e60ef242a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:32BUO7JCVPMPEBIHCKWGBXHK5Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Text GANs as Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gavriel Habib, Guy Tevet, Jonathan Berant, Vered Shwartz","submitted_at":"2018-10-30T11:58:16Z","abstract_excerpt":"Generative Adversarial Networks (GANs) are a promising approach for text generation that, unlike traditional language models (LM), does not suffer from the problem of ``exposure bias''. However, A major hurdle for understanding the potential of GANs for text generation is the lack of a clear evaluation metric. In this work, we propose to approximate the distribution of text generated by a GAN, which permits evaluating them with traditional probability-based LM metrics. We apply our approximation procedure on several GAN-based models and show that they currently perform substantially worse than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12686","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":"2026-05-17T23:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKrwODu3UawAq35MN9fIKaR0/QBQqDGx8DTpakRGfOtP1cKFbxaWvhlkTuxbDeo9urpyrKiuWXAiRXEtmcgfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:49:11.114864Z"},"content_sha256":"1231cd954a7bf549f64a1ab5ebb61fc35c4002bbc586d1cc84a79fba5f17b613","schema_version":"1.0","event_id":"sha256:1231cd954a7bf549f64a1ab5ebb61fc35c4002bbc586d1cc84a79fba5f17b613"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32BUO7JCVPMPEBIHCKWGBXHK5Y/bundle.json","state_url":"https://pith.science/pith/32BUO7JCVPMPEBIHCKWGBXHK5Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32BUO7JCVPMPEBIHCKWGBXHK5Y/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":"2026-05-30T08:49:11Z","links":{"resolver":"https://pith.science/pith/32BUO7JCVPMPEBIHCKWGBXHK5Y","bundle":"https://pith.science/pith/32BUO7JCVPMPEBIHCKWGBXHK5Y/bundle.json","state":"https://pith.science/pith/32BUO7JCVPMPEBIHCKWGBXHK5Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32BUO7JCVPMPEBIHCKWGBXHK5Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:32BUO7JCVPMPEBIHCKWGBXHK5Y","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":"4e1509fe33c1f44ec18ab49656b4eaac556cc431e586ad87ce86e5c403450b1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T11:58:16Z","title_canon_sha256":"55383921803f63e0573cf0dfa68d4bc6660ecb965accb68f64d406fab4b16767"},"schema_version":"1.0","source":{"id":"1810.12686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12686","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12686v2","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12686","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"32BUO7JCVPMP","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"32BUO7JCVPMPEBIH","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"32BUO7JC","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:1231cd954a7bf549f64a1ab5ebb61fc35c4002bbc586d1cc84a79fba5f17b613","target":"graph","created_at":"2026-05-17T23:50:38Z","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":"Generative Adversarial Networks (GANs) are a promising approach for text generation that, unlike traditional language models (LM), does not suffer from the problem of ``exposure bias''. However, A major hurdle for understanding the potential of GANs for text generation is the lack of a clear evaluation metric. In this work, we propose to approximate the distribution of text generated by a GAN, which permits evaluating them with traditional probability-based LM metrics. We apply our approximation procedure on several GAN-based models and show that they currently perform substantially worse than","authors_text":"Gavriel Habib, Guy Tevet, Jonathan Berant, Vered Shwartz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T11:58:16Z","title":"Evaluating Text GANs as Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12686","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:d6a51c8deb88e5e27830f4b3347da0beea6e54647bd12dee6bba994e60ef242a","target":"record","created_at":"2026-05-17T23:50:38Z","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":"4e1509fe33c1f44ec18ab49656b4eaac556cc431e586ad87ce86e5c403450b1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T11:58:16Z","title_canon_sha256":"55383921803f63e0573cf0dfa68d4bc6660ecb965accb68f64d406fab4b16767"},"schema_version":"1.0","source":{"id":"1810.12686","kind":"arxiv","version":2}},"canonical_sha256":"de83477d22abd8f2050712ac60dceaee25ae13ae2f49dce0915d8907467548d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de83477d22abd8f2050712ac60dceaee25ae13ae2f49dce0915d8907467548d9","first_computed_at":"2026-05-17T23:50:38.398974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:38.398974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7yDA9csxNu19GECwnUijdgeI1YODfagFigT+qo5fHolVc8aS98kiPQYRpfKRCXfNxdgER8d2GV42/6VaNVN6CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:38.399482Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6a51c8deb88e5e27830f4b3347da0beea6e54647bd12dee6bba994e60ef242a","sha256:1231cd954a7bf549f64a1ab5ebb61fc35c4002bbc586d1cc84a79fba5f17b613"],"state_sha256":"b3e39216a0409bb44b7ce1453dffef31ce89ffb4fd2c0151fb82c8827d436dd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8rmJqC6KBbbCFLP1ZNcKud7cbfR3Q+7mvNNuJa3YP0Mgl2owvA1BKYv1CDJz0wXAsJerU6t+rAFHQRGyXyuyBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:49:11.118222Z","bundle_sha256":"bd05a4caa071d9afec7f422210d57b9b3fd65ad3849dd051b56a41ac003bf90a"}}