{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3X2OFTIFROYUP7BQVYRU3VENAF","short_pith_number":"pith:3X2OFTIF","canonical_record":{"source":{"id":"2305.19847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T13:36:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"046c78911d090de513981e3476a8eeb779da3630281bce457e386bf09e095a78","abstract_canon_sha256":"1aa93a6ba693a7499a765ce51cd80b73a499438cec12d008f9144748e4166183"},"schema_version":"1.0"},"canonical_sha256":"ddf4e2cd058bb147fc30ae234dd48d0170ada8eab0a3812e4106fa49f8a7a882","source":{"kind":"arxiv","id":"2305.19847","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19847","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19847v1","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19847","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"pith_short_12","alias_value":"3X2OFTIFROYU","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"pith_short_16","alias_value":"3X2OFTIFROYUP7BQ","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"pith_short_8","alias_value":"3X2OFTIF","created_at":"2026-07-05T06:16:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3X2OFTIFROYUP7BQVYRU3VENAF","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T13:36:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"046c78911d090de513981e3476a8eeb779da3630281bce457e386bf09e095a78","abstract_canon_sha256":"1aa93a6ba693a7499a765ce51cd80b73a499438cec12d008f9144748e4166183"},"schema_version":"1.0"},"canonical_sha256":"ddf4e2cd058bb147fc30ae234dd48d0170ada8eab0a3812e4106fa49f8a7a882","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:03.940706Z","signature_b64":"mqxmhRY8JVU8pbBXIHMTLYH4cJfNRF+9lY8OuGEBwTINP8O0Cquk6gUK/CQM4fpX7iVskeFaTVXmJJ+YBCysDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddf4e2cd058bb147fc30ae234dd48d0170ada8eab0a3812e4106fa49f8a7a882","last_reissued_at":"2026-07-05T06:16:03.940208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:03.940208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19847","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":"2026-07-05T06:16:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lN/PvNAD1wy+MgwKzxahh47kan9Wkaiu4YDJ3USvFMeiZQ0d7Z4dyGH6XJWMVt0M3y0e1nQzgWTKrQc0TnaSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:18:50.181909Z"},"content_sha256":"b93a69590b7a46bd1b6d39d3cbe26cc7bb2a98ce0fcf3abe68c626fd24134ccd","schema_version":"1.0","event_id":"sha256:b93a69590b7a46bd1b6d39d3cbe26cc7bb2a98ce0fcf3abe68c626fd24134ccd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3X2OFTIFROYUP7BQVYRU3VENAF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Does Pretraining Improve Discourse-Aware Translation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Longyue Wang, Siyou Liu, Zhihong Huang","submitted_at":"2023-05-31T13:36:51Z","abstract_excerpt":"Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language translation. However, the underlying reasons for their strong performance have not been well explained. To bridge this gap, we introduce a probing task to interpret the ability of PLMs to capture discourse relation knowledge. We validate three state-of-the-art PLMs across encoder-, decoder-, and encoder-decoder-based models. The analysis shows that (1) the ability of PLMs on discourse modelling varies from architecture "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19847","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.19847/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":"2026-07-05T06:16:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ASjmSM0r/eJkRFbjHTF1iNQsYeGVhsK7ipTcYeOvxLRWsHIs5cPCuGf5lBIzh1ZFRZ6YoWyC2+b0J+Y//abiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:18:50.182945Z"},"content_sha256":"09509e33a34b1b04d3ce97ce79fff7d25592e525b7ab910de9d0113da59333f3","schema_version":"1.0","event_id":"sha256:09509e33a34b1b04d3ce97ce79fff7d25592e525b7ab910de9d0113da59333f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3X2OFTIFROYUP7BQVYRU3VENAF/bundle.json","state_url":"https://pith.science/pith/3X2OFTIFROYUP7BQVYRU3VENAF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3X2OFTIFROYUP7BQVYRU3VENAF/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":"2026-08-13T11:18:50Z","links":{"resolver":"https://pith.science/pith/3X2OFTIFROYUP7BQVYRU3VENAF","bundle":"https://pith.science/pith/3X2OFTIFROYUP7BQVYRU3VENAF/bundle.json","state":"https://pith.science/pith/3X2OFTIFROYUP7BQVYRU3VENAF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3X2OFTIFROYUP7BQVYRU3VENAF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3X2OFTIFROYUP7BQVYRU3VENAF","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":"1aa93a6ba693a7499a765ce51cd80b73a499438cec12d008f9144748e4166183","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T13:36:51Z","title_canon_sha256":"046c78911d090de513981e3476a8eeb779da3630281bce457e386bf09e095a78"},"schema_version":"1.0","source":{"id":"2305.19847","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19847","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19847v1","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19847","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"pith_short_12","alias_value":"3X2OFTIFROYU","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"pith_short_16","alias_value":"3X2OFTIFROYUP7BQ","created_at":"2026-07-05T06:16:03Z"},{"alias_kind":"pith_short_8","alias_value":"3X2OFTIF","created_at":"2026-07-05T06:16:03Z"}],"graph_snapshots":[{"event_id":"sha256:09509e33a34b1b04d3ce97ce79fff7d25592e525b7ab910de9d0113da59333f3","target":"graph","created_at":"2026-07-05T06:16:03Z","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/2305.19847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language translation. However, the underlying reasons for their strong performance have not been well explained. To bridge this gap, we introduce a probing task to interpret the ability of PLMs to capture discourse relation knowledge. We validate three state-of-the-art PLMs across encoder-, decoder-, and encoder-decoder-based models. The analysis shows that (1) the ability of PLMs on discourse modelling varies from architecture ","authors_text":"Derek F. Wong, Longyue Wang, Siyou Liu, Zhihong Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T13:36:51Z","title":"How Does Pretraining Improve Discourse-Aware Translation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19847","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:b93a69590b7a46bd1b6d39d3cbe26cc7bb2a98ce0fcf3abe68c626fd24134ccd","target":"record","created_at":"2026-07-05T06:16:03Z","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":"1aa93a6ba693a7499a765ce51cd80b73a499438cec12d008f9144748e4166183","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T13:36:51Z","title_canon_sha256":"046c78911d090de513981e3476a8eeb779da3630281bce457e386bf09e095a78"},"schema_version":"1.0","source":{"id":"2305.19847","kind":"arxiv","version":1}},"canonical_sha256":"ddf4e2cd058bb147fc30ae234dd48d0170ada8eab0a3812e4106fa49f8a7a882","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddf4e2cd058bb147fc30ae234dd48d0170ada8eab0a3812e4106fa49f8a7a882","first_computed_at":"2026-07-05T06:16:03.940208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:03.940208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mqxmhRY8JVU8pbBXIHMTLYH4cJfNRF+9lY8OuGEBwTINP8O0Cquk6gUK/CQM4fpX7iVskeFaTVXmJJ+YBCysDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:03.940706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19847","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b93a69590b7a46bd1b6d39d3cbe26cc7bb2a98ce0fcf3abe68c626fd24134ccd","sha256:09509e33a34b1b04d3ce97ce79fff7d25592e525b7ab910de9d0113da59333f3"],"state_sha256":"021278938c00b1bdf8cf7514c8a439eaeb5f1023e36a6cf2a3c91c2a6f917454"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eqEFwzBTgARW+0ZmcHAVTnew9jTq4CE6WVql/mQGt8AlKoEYVRoifT71usSWZXFjuLQ1j+GolDTHVp2In5RkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T11:18:50.190122Z","bundle_sha256":"e1d6bd60fdd82329eb8fa69972c90f58ef4e3e038948b033bed054308ce4194d"}}