{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CUFDYP7SH4TDO6YXOIT3NNYCC6","short_pith_number":"pith:CUFDYP7S","canonical_record":{"source":{"id":"1808.09564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T22:30:11Z","cross_cats_sorted":[],"title_canon_sha256":"7de1d602400cc5ce6ae6dc583360467b87e5fd8f5bd571f3cd1cec851ac99654","abstract_canon_sha256":"6e3b2b417b73646de6e04859b240ef45842aa0e97ff38d15bb8797d5e41395f6"},"schema_version":"1.0"},"canonical_sha256":"150a3c3ff23f26377b177227b6b70217b7ebdbc076d9f00e25fb6d517ba14621","source":{"kind":"arxiv","id":"1808.09564","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09564","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09564v1","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09564","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"pith_short_12","alias_value":"CUFDYP7SH4TD","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CUFDYP7SH4TDO6YX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CUFDYP7S","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CUFDYP7SH4TDO6YXOIT3NNYCC6","target":"record","payload":{"canonical_record":{"source":{"id":"1808.09564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T22:30:11Z","cross_cats_sorted":[],"title_canon_sha256":"7de1d602400cc5ce6ae6dc583360467b87e5fd8f5bd571f3cd1cec851ac99654","abstract_canon_sha256":"6e3b2b417b73646de6e04859b240ef45842aa0e97ff38d15bb8797d5e41395f6"},"schema_version":"1.0"},"canonical_sha256":"150a3c3ff23f26377b177227b6b70217b7ebdbc076d9f00e25fb6d517ba14621","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:55.171061Z","signature_b64":"OcNByp7ptByAOlSstdWFWxugrLJvyC1icNTdcv1Hsj+eCi3OSq4nHP8n69giuIrzVoCpvBVJB1hXyerJlFh2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"150a3c3ff23f26377b177227b6b70217b7ebdbc076d9f00e25fb6d517ba14621","last_reissued_at":"2026-05-18T00:06:55.170310Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:55.170310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.09564","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LuebBa+eyznmisxGKAl2ppnIiOwykTJLUYecgCRekP1oWOFmfSUdXKct5W7zx1ivAN6KRchaG2E0k5t0QymuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:50:54.405744Z"},"content_sha256":"c2a73b37a864b1c8b8d219f846dc99142e694ca7a2eb1d15efcf4548e4b1d449","schema_version":"1.0","event_id":"sha256:c2a73b37a864b1c8b8d219f846dc99142e694ca7a2eb1d15efcf4548e4b1d449"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CUFDYP7SH4TDO6YXOIT3NNYCC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Huang, Mingbo Ma, Renjie Zheng","submitted_at":"2018-08-28T22:30:11Z","abstract_excerpt":"Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though there are often multiple references available, e.g., 4 references in NIST MT evaluations, and 5 references in image captioning data. We first investigate several different ways of utilizing multiple human references during training. But more importantly, we then propose an algorithm to generate exponentially many pseudo-references by first compressing existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09564","kind":"arxiv","version":1},"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":"2026-05-18T00:06:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PEgkOEc8JCuUv1WObLfJ1nu7Z2o81aaFsSy7WRCMNixGeYtQ5akfvx+IhpJ5B6JAzyA22i9O4Pf+fsNIseDNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:50:54.406281Z"},"content_sha256":"62610311859e95f6de3acbdb9b067d460d31367ddbfbcfa99b37d28b81902c51","schema_version":"1.0","event_id":"sha256:62610311859e95f6de3acbdb9b067d460d31367ddbfbcfa99b37d28b81902c51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUFDYP7SH4TDO6YXOIT3NNYCC6/bundle.json","state_url":"https://pith.science/pith/CUFDYP7SH4TDO6YXOIT3NNYCC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUFDYP7SH4TDO6YXOIT3NNYCC6/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":"2026-06-02T07:50:54Z","links":{"resolver":"https://pith.science/pith/CUFDYP7SH4TDO6YXOIT3NNYCC6","bundle":"https://pith.science/pith/CUFDYP7SH4TDO6YXOIT3NNYCC6/bundle.json","state":"https://pith.science/pith/CUFDYP7SH4TDO6YXOIT3NNYCC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUFDYP7SH4TDO6YXOIT3NNYCC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CUFDYP7SH4TDO6YXOIT3NNYCC6","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":"6e3b2b417b73646de6e04859b240ef45842aa0e97ff38d15bb8797d5e41395f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T22:30:11Z","title_canon_sha256":"7de1d602400cc5ce6ae6dc583360467b87e5fd8f5bd571f3cd1cec851ac99654"},"schema_version":"1.0","source":{"id":"1808.09564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09564","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09564v1","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09564","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"pith_short_12","alias_value":"CUFDYP7SH4TD","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CUFDYP7SH4TDO6YX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CUFDYP7S","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:62610311859e95f6de3acbdb9b067d460d31367ddbfbcfa99b37d28b81902c51","target":"graph","created_at":"2026-05-18T00:06:55Z","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"},"paper":{"abstract_excerpt":"Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though there are often multiple references available, e.g., 4 references in NIST MT evaluations, and 5 references in image captioning data. We first investigate several different ways of utilizing multiple human references during training. But more importantly, we then propose an algorithm to generate exponentially many pseudo-references by first compressing existin","authors_text":"Liang Huang, Mingbo Ma, Renjie Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T22:30:11Z","title":"Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09564","kind":"arxiv","version":1},"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:c2a73b37a864b1c8b8d219f846dc99142e694ca7a2eb1d15efcf4548e4b1d449","target":"record","created_at":"2026-05-18T00:06:55Z","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":"6e3b2b417b73646de6e04859b240ef45842aa0e97ff38d15bb8797d5e41395f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T22:30:11Z","title_canon_sha256":"7de1d602400cc5ce6ae6dc583360467b87e5fd8f5bd571f3cd1cec851ac99654"},"schema_version":"1.0","source":{"id":"1808.09564","kind":"arxiv","version":1}},"canonical_sha256":"150a3c3ff23f26377b177227b6b70217b7ebdbc076d9f00e25fb6d517ba14621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"150a3c3ff23f26377b177227b6b70217b7ebdbc076d9f00e25fb6d517ba14621","first_computed_at":"2026-05-18T00:06:55.170310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:55.170310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OcNByp7ptByAOlSstdWFWxugrLJvyC1icNTdcv1Hsj+eCi3OSq4nHP8n69giuIrzVoCpvBVJB1hXyerJlFh2BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:55.171061Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2a73b37a864b1c8b8d219f846dc99142e694ca7a2eb1d15efcf4548e4b1d449","sha256:62610311859e95f6de3acbdb9b067d460d31367ddbfbcfa99b37d28b81902c51"],"state_sha256":"981b09fc27cd7bd5b3b402ad94536e1f38021dd75104b2b31edc93560c928a40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLOVdczlH3B4pN3kZcmj5gE13tbIVxtQkNTOXRkdn+Npw+p/eU0mYbUDoeg/pBUA9APPNjC41U0AaWs+MkifDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T07:50:54.408882Z","bundle_sha256":"a5fea2ede88cc7f499b15fa4d9cd8bbd77c462db3be8b77129c1ac3d395a53db"}}