{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HHHWKTOZK5U5RWA6SNCW2V5AWR","short_pith_number":"pith:HHHWKTOZ","canonical_record":{"source":{"id":"1906.03351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T22:45:33Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"bd66104b1e005f56a96efa3714e513e6199b27768cb6a773f19eb2be68d391b6","abstract_canon_sha256":"beefdd90a68ca31533f8b7e01c3ac9278d0dbe6478dd99833d382dafc9d2cfcf"},"schema_version":"1.0"},"canonical_sha256":"39cf654dd95769d8d81e93456d57a0b4786585b36921e042fa166fb29b6e1124","source":{"kind":"arxiv","id":"1906.03351","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03351","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03351v2","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03351","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"HHHWKTOZK5U5","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"pith_short_16","alias_value":"HHHWKTOZK5U5RWA6","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"pith_short_8","alias_value":"HHHWKTOZ","created_at":"2026-07-05T00:21:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HHHWKTOZK5U5RWA6SNCW2V5AWR","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T22:45:33Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"bd66104b1e005f56a96efa3714e513e6199b27768cb6a773f19eb2be68d391b6","abstract_canon_sha256":"beefdd90a68ca31533f8b7e01c3ac9278d0dbe6478dd99833d382dafc9d2cfcf"},"schema_version":"1.0"},"canonical_sha256":"39cf654dd95769d8d81e93456d57a0b4786585b36921e042fa166fb29b6e1124","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:35.055304Z","signature_b64":"9b8ZM2bqsejBWeDdjTSip1Rzg3Jo5pXPr6Cc14G/NdRnIOrHJj+yMbxHFqZw1GS/1+/e4i3nEuEIUrQj+up4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39cf654dd95769d8d81e93456d57a0b4786585b36921e042fa166fb29b6e1124","last_reissued_at":"2026-07-05T00:21:35.054857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:35.054857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03351","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":"2026-07-05T00:21:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNCcn+5LlAE6WBOsdf3COnVPA+k8qK4orEYt4Fwl9lSMhG6ieGHX7PqR8I8bsvHj0FdEfSQwJQm/qMlK3Y6mDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:56.012716Z"},"content_sha256":"eda0c66e9b6c14c1c910e25bdbfbe3f8e954ec0a0dc065b67bae11bcf52fff83","schema_version":"1.0","event_id":"sha256:eda0c66e9b6c14c1c910e25bdbfbe3f8e954ec0a0dc065b67bae11bcf52fff83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HHHWKTOZK5U5RWA6SNCW2V5AWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Real or Fake? Learning to Discriminate Machine from Human Generated Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anton Bakhtin, Arthur Szlam, Marc'Aurelio Ranzato, Myle Ott, Sam Gross, Yuntian Deng","submitted_at":"2019-06-07T22:45:33Z","abstract_excerpt":"Energy-based models (EBMs), a.k.a. un-normalized models, have had recent successes in continuous spaces. However, they have not been successfully applied to model text sequences. While decreasing the energy at training samples is straightforward, mining (negative) samples where the energy should be increased is difficult. In part, this is because standard gradient-based methods are not readily applicable when the input is high-dimensional and discrete. Here, we side-step this issue by generating negatives using pre-trained auto-regressive language models. The EBM then works in the residual of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03351","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.03351/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":"2026-07-05T00:21:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MoO+m58yMA5Sqj+CxdXnf+MhjIUxqKpqQJIQ4I+ljBVXlfvukQ0YMHwOqes8I+YsAIrz8kMMQMDvQSOjVw0ZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:56.014407Z"},"content_sha256":"0687bca093d13d99391af693f072b12180b435221a9fb7f71ff38edbbdb3301f","schema_version":"1.0","event_id":"sha256:0687bca093d13d99391af693f072b12180b435221a9fb7f71ff38edbbdb3301f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHHWKTOZK5U5RWA6SNCW2V5AWR/bundle.json","state_url":"https://pith.science/pith/HHHWKTOZK5U5RWA6SNCW2V5AWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHHWKTOZK5U5RWA6SNCW2V5AWR/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":"2026-08-08T12:55:56Z","links":{"resolver":"https://pith.science/pith/HHHWKTOZK5U5RWA6SNCW2V5AWR","bundle":"https://pith.science/pith/HHHWKTOZK5U5RWA6SNCW2V5AWR/bundle.json","state":"https://pith.science/pith/HHHWKTOZK5U5RWA6SNCW2V5AWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHHWKTOZK5U5RWA6SNCW2V5AWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HHHWKTOZK5U5RWA6SNCW2V5AWR","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":"beefdd90a68ca31533f8b7e01c3ac9278d0dbe6478dd99833d382dafc9d2cfcf","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T22:45:33Z","title_canon_sha256":"bd66104b1e005f56a96efa3714e513e6199b27768cb6a773f19eb2be68d391b6"},"schema_version":"1.0","source":{"id":"1906.03351","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03351","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03351v2","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03351","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"HHHWKTOZK5U5","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"pith_short_16","alias_value":"HHHWKTOZK5U5RWA6","created_at":"2026-07-05T00:21:35Z"},{"alias_kind":"pith_short_8","alias_value":"HHHWKTOZ","created_at":"2026-07-05T00:21:35Z"}],"graph_snapshots":[{"event_id":"sha256:0687bca093d13d99391af693f072b12180b435221a9fb7f71ff38edbbdb3301f","target":"graph","created_at":"2026-07-05T00:21:35Z","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/1906.03351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Energy-based models (EBMs), a.k.a. un-normalized models, have had recent successes in continuous spaces. However, they have not been successfully applied to model text sequences. While decreasing the energy at training samples is straightforward, mining (negative) samples where the energy should be increased is difficult. In part, this is because standard gradient-based methods are not readily applicable when the input is high-dimensional and discrete. Here, we side-step this issue by generating negatives using pre-trained auto-regressive language models. The EBM then works in the residual of ","authors_text":"Anton Bakhtin, Arthur Szlam, Marc'Aurelio Ranzato, Myle Ott, Sam Gross, Yuntian Deng","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T22:45:33Z","title":"Real or Fake? Learning to Discriminate Machine from Human Generated Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03351","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:eda0c66e9b6c14c1c910e25bdbfbe3f8e954ec0a0dc065b67bae11bcf52fff83","target":"record","created_at":"2026-07-05T00:21:35Z","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":"beefdd90a68ca31533f8b7e01c3ac9278d0dbe6478dd99833d382dafc9d2cfcf","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T22:45:33Z","title_canon_sha256":"bd66104b1e005f56a96efa3714e513e6199b27768cb6a773f19eb2be68d391b6"},"schema_version":"1.0","source":{"id":"1906.03351","kind":"arxiv","version":2}},"canonical_sha256":"39cf654dd95769d8d81e93456d57a0b4786585b36921e042fa166fb29b6e1124","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39cf654dd95769d8d81e93456d57a0b4786585b36921e042fa166fb29b6e1124","first_computed_at":"2026-07-05T00:21:35.054857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:21:35.054857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9b8ZM2bqsejBWeDdjTSip1Rzg3Jo5pXPr6Cc14G/NdRnIOrHJj+yMbxHFqZw1GS/1+/e4i3nEuEIUrQj+up4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:21:35.055304Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03351","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eda0c66e9b6c14c1c910e25bdbfbe3f8e954ec0a0dc065b67bae11bcf52fff83","sha256:0687bca093d13d99391af693f072b12180b435221a9fb7f71ff38edbbdb3301f"],"state_sha256":"d30f77777c8573fd89d2a5b3d65f7ddc9f2f4ec9d5f824aa0e2dfdd36bfefc7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/JHH768vWjJpFOYwKfXGXUGR9rruSv9DOkyL+NBmEpvL8qm3/V0QnHjYH1fnywZUiOJkIzL3WgN056j47hdAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:55:56.019966Z","bundle_sha256":"f48d469d57660309f6dad95bb1a2622a846363ab9bcbc1c2365bd73119420e77"}}