{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SEO2CS7OM7MLQPVFEL43HKMUZ2","short_pith_number":"pith:SEO2CS7O","canonical_record":{"source":{"id":"1909.07063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-16T08:46:30Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"eed06a5ecef0d616911b5cbe16013d4706728331cd38ddd60af60dfe99326d99","abstract_canon_sha256":"97ace0212de407d48cd6469babe95229d6973a253b0722a17a9b666f7ff0573e"},"schema_version":"1.0"},"canonical_sha256":"911da14bee67d8b83ea522f9b3a994cea6f82079a9b29cbeae698c5147097530","source":{"kind":"arxiv","id":"1909.07063","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.07063","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1909.07063v2","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07063","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"SEO2CS7OM7ML","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"SEO2CS7OM7MLQPVF","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"SEO2CS7O","created_at":"2026-07-05T00:05:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SEO2CS7OM7MLQPVFEL43HKMUZ2","target":"record","payload":{"canonical_record":{"source":{"id":"1909.07063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-16T08:46:30Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"eed06a5ecef0d616911b5cbe16013d4706728331cd38ddd60af60dfe99326d99","abstract_canon_sha256":"97ace0212de407d48cd6469babe95229d6973a253b0722a17a9b666f7ff0573e"},"schema_version":"1.0"},"canonical_sha256":"911da14bee67d8b83ea522f9b3a994cea6f82079a9b29cbeae698c5147097530","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:55.365356Z","signature_b64":"zQJec9o0AlopFytzGT46RINSbDx0FxVi/CoGtDZNBvjR3OJc579r1lDfKISRJ06F/lc2lwBboWLXQzwJKdOqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"911da14bee67d8b83ea522f9b3a994cea6f82079a9b29cbeae698c5147097530","last_reissued_at":"2026-07-05T00:05:55.364914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:55.364914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.07063","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":"2026-07-05T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VelMuBK/P/lqKC2w/wNUjv5A7sHV+38qjrlR1nL/EHIH32vYeNvXOEeLORU9G/J2H3qX/nngj9hhLFQUvpmIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T05:58:35.955919Z"},"content_sha256":"22bbde3d40c1688b14b8daaa5ce8dfb61b73e3e2f2a26cde2fc01dadf6b9760e","schema_version":"1.0","event_id":"sha256:22bbde3d40c1688b14b8daaa5ce8dfb61b73e3e2f2a26cde2fc01dadf6b9760e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SEO2CS7OM7MLQPVFEL43HKMUZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Global Autoregressive Models for Data-Efficient Sequence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jean-Marc Andreoli, Marc Dymetman, Tetiana Parshakova","submitted_at":"2019-09-16T08:46:30Z","abstract_excerpt":"Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs (Global Autoregressive Models), which combine an autoregressive component with a log-linear component, allowing the use of global \\textit{a priori} features to compensate for lack of data. We train these models in two steps. In the first step, we obtain an \\emph{unnormalized} GAM that maximizes the likelihood of the data, but is improper for fast inference or evaluation. In the second step, we use this GAM to train "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07063","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/1909.07063/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":"2026-07-05T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VnJZu6QE+yP1pwuVB6/MbLClH28o5FLxZBNH46s9P1dEIsuPbZirusKeNUzTzKp8VjJsoP0yMAgpUB6lCZq9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T05:58:35.956606Z"},"content_sha256":"057443baafe1eaf8ef16b5f9d027194a97ce6f539e8222cc1ad5f653982f86c2","schema_version":"1.0","event_id":"sha256:057443baafe1eaf8ef16b5f9d027194a97ce6f539e8222cc1ad5f653982f86c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SEO2CS7OM7MLQPVFEL43HKMUZ2/bundle.json","state_url":"https://pith.science/pith/SEO2CS7OM7MLQPVFEL43HKMUZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SEO2CS7OM7MLQPVFEL43HKMUZ2/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":"2026-07-11T05:58:35Z","links":{"resolver":"https://pith.science/pith/SEO2CS7OM7MLQPVFEL43HKMUZ2","bundle":"https://pith.science/pith/SEO2CS7OM7MLQPVFEL43HKMUZ2/bundle.json","state":"https://pith.science/pith/SEO2CS7OM7MLQPVFEL43HKMUZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SEO2CS7OM7MLQPVFEL43HKMUZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SEO2CS7OM7MLQPVFEL43HKMUZ2","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":"97ace0212de407d48cd6469babe95229d6973a253b0722a17a9b666f7ff0573e","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-16T08:46:30Z","title_canon_sha256":"eed06a5ecef0d616911b5cbe16013d4706728331cd38ddd60af60dfe99326d99"},"schema_version":"1.0","source":{"id":"1909.07063","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.07063","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1909.07063v2","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07063","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"SEO2CS7OM7ML","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"SEO2CS7OM7MLQPVF","created_at":"2026-07-05T00:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"SEO2CS7O","created_at":"2026-07-05T00:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:057443baafe1eaf8ef16b5f9d027194a97ce6f539e8222cc1ad5f653982f86c2","target":"graph","created_at":"2026-07-05T00:05:55Z","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/1909.07063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs (Global Autoregressive Models), which combine an autoregressive component with a log-linear component, allowing the use of global \\textit{a priori} features to compensate for lack of data. We train these models in two steps. In the first step, we obtain an \\emph{unnormalized} GAM that maximizes the likelihood of the data, but is improper for fast inference or evaluation. In the second step, we use this GAM to train ","authors_text":"Jean-Marc Andreoli, Marc Dymetman, Tetiana Parshakova","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-16T08:46:30Z","title":"Global Autoregressive Models for Data-Efficient Sequence Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07063","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":"sha256:22bbde3d40c1688b14b8daaa5ce8dfb61b73e3e2f2a26cde2fc01dadf6b9760e","target":"record","created_at":"2026-07-05T00:05:55Z","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":"97ace0212de407d48cd6469babe95229d6973a253b0722a17a9b666f7ff0573e","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-16T08:46:30Z","title_canon_sha256":"eed06a5ecef0d616911b5cbe16013d4706728331cd38ddd60af60dfe99326d99"},"schema_version":"1.0","source":{"id":"1909.07063","kind":"arxiv","version":2}},"canonical_sha256":"911da14bee67d8b83ea522f9b3a994cea6f82079a9b29cbeae698c5147097530","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"911da14bee67d8b83ea522f9b3a994cea6f82079a9b29cbeae698c5147097530","first_computed_at":"2026-07-05T00:05:55.364914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:05:55.364914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zQJec9o0AlopFytzGT46RINSbDx0FxVi/CoGtDZNBvjR3OJc579r1lDfKISRJ06F/lc2lwBboWLXQzwJKdOqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:05:55.365356Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.07063","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22bbde3d40c1688b14b8daaa5ce8dfb61b73e3e2f2a26cde2fc01dadf6b9760e","sha256:057443baafe1eaf8ef16b5f9d027194a97ce6f539e8222cc1ad5f653982f86c2"],"state_sha256":"9d1c2560d4f0553d674b4511203f6683da51766a6eeda5db7dc3e8ce4ea7fff2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+RIejQOCmFqAlOFNOTzzunZrSLj3Hw9a94PrRDrsEjWdkUF0x9BRLPDcExKr7f7aUZ1GLyrFDo5/oYca4CSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T05:58:35.960545Z","bundle_sha256":"2eea80941d0efcad1cf39b88b222963d4eba32b9e14812a4f20bf7a3cb3cef32"}}