{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CWPNPPNQZDJALPOUPAN4KJWSKG","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":"7287d362bd71f6946575b3f4c22855608c5368d03efcfcc5342087374509d0f9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-29T14:26:59Z","title_canon_sha256":"c8ae30cba4a577a12e1aaffff0a1d772c88ef691c5e7e3bf212e3aa3afe4b3fd"},"schema_version":"1.0","source":{"id":"2012.14768","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.14768","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2012.14768v2","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14768","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"CWPNPPNQZDJA","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"CWPNPPNQZDJALPOU","created_at":"2026-07-05T02:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"CWPNPPNQ","created_at":"2026-07-05T02:24:13Z"}],"graph_snapshots":[{"event_id":"sha256:25add5eac2a9448bc3ec2ee45ce801d3afe6c1bb321bf992d50fc9e94082f741","target":"graph","created_at":"2026-07-05T02:24:13Z","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/2012.14768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Encoder layer fusion (EncoderFusion) is a technique to fuse all the encoder layers (instead of the uppermost layer) for sequence-to-sequence (Seq2Seq) models, which has proven effective on various NLP tasks. However, it is still not entirely clear why and when EncoderFusion should work. In this paper, our main contribution is to take a step further in understanding EncoderFusion. Many of previous studies believe that the success of EncoderFusion comes from exploiting surface and syntactic information embedded in lower encoder layers. Unlike them, we find that the encoder embedding layer is mor","authors_text":"Derek F. Wong, Liang Ding, Lidia S. Chao, Longyue Wang, Xuebo Liu, Zhaopeng Tu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-29T14:26:59Z","title":"Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14768","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":"sha256:32946aee9373a10218958d7e8bcb7b44665e7324b056e586353437c671f4767b","target":"record","created_at":"2026-07-05T02:24:13Z","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":"7287d362bd71f6946575b3f4c22855608c5368d03efcfcc5342087374509d0f9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-29T14:26:59Z","title_canon_sha256":"c8ae30cba4a577a12e1aaffff0a1d772c88ef691c5e7e3bf212e3aa3afe4b3fd"},"schema_version":"1.0","source":{"id":"2012.14768","kind":"arxiv","version":2}},"canonical_sha256":"159ed7bdb0c8d205bdd4781bc526d2518cf47dfcde7f33692c93926ce906ac32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"159ed7bdb0c8d205bdd4781bc526d2518cf47dfcde7f33692c93926ce906ac32","first_computed_at":"2026-07-05T02:24:13.209906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:13.209906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jV+z48G3dE1FvSD5SoQKbQlCRRbF5lfM3GmOOY4cWrkd0WMBwxwV39cWeZJTA4AC9c5vvfZLntXkge0rn1OAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:13.210401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.14768","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32946aee9373a10218958d7e8bcb7b44665e7324b056e586353437c671f4767b","sha256:25add5eac2a9448bc3ec2ee45ce801d3afe6c1bb321bf992d50fc9e94082f741"],"state_sha256":"b4778321f7838b3ea03e38bb275c1a0aa261b8000e5b1a32e34330c0d83a7416"}