{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SGJMGHQXB7XXIPZSLCA5IDZWUV","short_pith_number":"pith:SGJMGHQX","canonical_record":{"source":{"id":"1706.09152","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-28T07:44:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7bbb0e822477e05559dd72d0268374ada8074691f07b976648910923092337ea","abstract_canon_sha256":"93fe104505a49afeb71544a34263c91d58ab4aab902c2bc8934de26a9ae15483"},"schema_version":"1.0"},"canonical_sha256":"9192c31e170fef743f325881d40f36a5546f2263bcf8cd7fc069ae8ab150496a","source":{"kind":"arxiv","id":"1706.09152","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.09152","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"1706.09152v6","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.09152","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"SGJMGHQXB7XX","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SGJMGHQXB7XXIPZS","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SGJMGHQX","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SGJMGHQXB7XXIPZSLCA5IDZWUV","target":"record","payload":{"canonical_record":{"source":{"id":"1706.09152","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-28T07:44:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7bbb0e822477e05559dd72d0268374ada8074691f07b976648910923092337ea","abstract_canon_sha256":"93fe104505a49afeb71544a34263c91d58ab4aab902c2bc8934de26a9ae15483"},"schema_version":"1.0"},"canonical_sha256":"9192c31e170fef743f325881d40f36a5546f2263bcf8cd7fc069ae8ab150496a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:33.266570Z","signature_b64":"bXjeskRXLQlQug9xvjNlKpy7xnmZJ8YkLbgFsGkR0MbgRdCXY7xzSnbIKPqSfsrx1SVxnQx2iwg9F+Sz57xqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9192c31e170fef743f325881d40f36a5546f2263bcf8cd7fc069ae8ab150496a","last_reissued_at":"2026-05-17T23:59:33.265959Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:33.265959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.09152","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UY8nfyjOzpgE5fgME8o32Y4IDT+fqcp3/yV9ZwCN/eYhOQfPAmU2qn5ta29FQkDA8bjAojuOCLfwKpaNLfeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:20:02.426894Z"},"content_sha256":"b2a421e3f3b9810a572a6cc2c353e4b36459ffafd17651a9de6a031ee2dcf923","schema_version":"1.0","event_id":"sha256:b2a421e3f3b9810a572a6cc2c353e4b36459ffafd17651a9de6a031ee2dcf923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SGJMGHQXB7XXIPZSLCA5IDZWUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Bridging Network in Neural Sequence Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Guanlin Li, Ming Zhou, Mu Li, Shujie Liu, Shuo Ren, Wenhu Chen, Zhirui Zhang","submitted_at":"2017-06-28T07:44:17Z","abstract_excerpt":"In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE directly maximizing the conditional likelihood, the bridge extends the point-wise ground truth to a bridge distribution conditioned on it, and the generator is optimized to minimize their KL-divergence. Three different GBNs, namely uniform GBN, language-model GBN and coaching GBN, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.09152","kind":"arxiv","version":6},"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":"2026-05-17T23:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/2OKURmmVB131SPg5IZOnseXRqscqiXxPSX6t+JvO5rDIchJAO79npG73bDK4/04Sh8+LsS2IGIrSG3GBwKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:20:02.427307Z"},"content_sha256":"83b12f295fb2e4c49e379a37e3eae60b6ba4e3e68b6be7c252e985241805b527","schema_version":"1.0","event_id":"sha256:83b12f295fb2e4c49e379a37e3eae60b6ba4e3e68b6be7c252e985241805b527"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGJMGHQXB7XXIPZSLCA5IDZWUV/bundle.json","state_url":"https://pith.science/pith/SGJMGHQXB7XXIPZSLCA5IDZWUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGJMGHQXB7XXIPZSLCA5IDZWUV/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":"2026-05-27T14:20:02Z","links":{"resolver":"https://pith.science/pith/SGJMGHQXB7XXIPZSLCA5IDZWUV","bundle":"https://pith.science/pith/SGJMGHQXB7XXIPZSLCA5IDZWUV/bundle.json","state":"https://pith.science/pith/SGJMGHQXB7XXIPZSLCA5IDZWUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGJMGHQXB7XXIPZSLCA5IDZWUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SGJMGHQXB7XXIPZSLCA5IDZWUV","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":"93fe104505a49afeb71544a34263c91d58ab4aab902c2bc8934de26a9ae15483","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-28T07:44:17Z","title_canon_sha256":"7bbb0e822477e05559dd72d0268374ada8074691f07b976648910923092337ea"},"schema_version":"1.0","source":{"id":"1706.09152","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.09152","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"1706.09152v6","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.09152","created_at":"2026-05-17T23:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"SGJMGHQXB7XX","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SGJMGHQXB7XXIPZS","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SGJMGHQX","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:83b12f295fb2e4c49e379a37e3eae60b6ba4e3e68b6be7c252e985241805b527","target":"graph","created_at":"2026-05-17T23:59:33Z","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":"In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE directly maximizing the conditional likelihood, the bridge extends the point-wise ground truth to a bridge distribution conditioned on it, and the generator is optimized to minimize their KL-divergence. Three different GBNs, namely uniform GBN, language-model GBN and coaching GBN, ","authors_text":"Guanlin Li, Ming Zhou, Mu Li, Shujie Liu, Shuo Ren, Wenhu Chen, Zhirui Zhang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-28T07:44:17Z","title":"Generative Bridging Network in Neural Sequence Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.09152","kind":"arxiv","version":6},"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:b2a421e3f3b9810a572a6cc2c353e4b36459ffafd17651a9de6a031ee2dcf923","target":"record","created_at":"2026-05-17T23:59:33Z","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":"93fe104505a49afeb71544a34263c91d58ab4aab902c2bc8934de26a9ae15483","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-28T07:44:17Z","title_canon_sha256":"7bbb0e822477e05559dd72d0268374ada8074691f07b976648910923092337ea"},"schema_version":"1.0","source":{"id":"1706.09152","kind":"arxiv","version":6}},"canonical_sha256":"9192c31e170fef743f325881d40f36a5546f2263bcf8cd7fc069ae8ab150496a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9192c31e170fef743f325881d40f36a5546f2263bcf8cd7fc069ae8ab150496a","first_computed_at":"2026-05-17T23:59:33.265959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:33.265959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bXjeskRXLQlQug9xvjNlKpy7xnmZJ8YkLbgFsGkR0MbgRdCXY7xzSnbIKPqSfsrx1SVxnQx2iwg9F+Sz57xqDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:33.266570Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.09152","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2a421e3f3b9810a572a6cc2c353e4b36459ffafd17651a9de6a031ee2dcf923","sha256:83b12f295fb2e4c49e379a37e3eae60b6ba4e3e68b6be7c252e985241805b527"],"state_sha256":"ad0022ce27fa16b242ba9ebcc55d343732f16a036ae3b5898e04eb74c092da23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4vRVMOW6oKG1xfJHMHhem8u5lsD6TMZk6x3gg1+w/B6TyGlYfGBrKHNXM+nMKRO3CAymfBnjGjZzStiyhL1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:20:02.430871Z","bundle_sha256":"b9046d72e8843f06b5704584669bd2c7a1a23f2c2efa5084ddaa1e7731615c8f"}}