{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LCMOD54RL7N5WUMM6WO6NZIEAG","short_pith_number":"pith:LCMOD54R","canonical_record":{"source":{"id":"1709.03980","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T13:38:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"49f54a0e7b4b2e560d630c6183d1da2bce01e1923fc109b1599dad81201c8087","abstract_canon_sha256":"a1b9bf1e7f940cdcf4f7c99b1e35e8363bfbe640b523dbb960e2c2e686f723cf"},"schema_version":"1.0"},"canonical_sha256":"5898e1f7915fdbdb518cf59de6e5040191ab39f5ad22752d41365792ca1b05be","source":{"kind":"arxiv","id":"1709.03980","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03980","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03980v3","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03980","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"LCMOD54RL7N5","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LCMOD54RL7N5WUMM","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LCMOD54R","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LCMOD54RL7N5WUMM6WO6NZIEAG","target":"record","payload":{"canonical_record":{"source":{"id":"1709.03980","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T13:38:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"49f54a0e7b4b2e560d630c6183d1da2bce01e1923fc109b1599dad81201c8087","abstract_canon_sha256":"a1b9bf1e7f940cdcf4f7c99b1e35e8363bfbe640b523dbb960e2c2e686f723cf"},"schema_version":"1.0"},"canonical_sha256":"5898e1f7915fdbdb518cf59de6e5040191ab39f5ad22752d41365792ca1b05be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:59.870677Z","signature_b64":"0F6VKi9OkoJWLUoMMnx/BsSlh3CgVOYs+I59vgK0HKm3ua1z/3hbjk5FlCASavA/eX4z49f7tc/xMTLs5+sUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5898e1f7915fdbdb518cf59de6e5040191ab39f5ad22752d41365792ca1b05be","last_reissued_at":"2026-05-18T00:14:59.870026Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:59.870026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.03980","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaXx0nKCSKvnnoyV9ZGI+tC2iOvjPOk5rOnfzJlSe/htGKXM+fpGW1M/TA8yCpjb55yC+cTnDz0haljKB4eQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:55:43.023807Z"},"content_sha256":"45d48c6a1a9a1e6a5b426f1b27cf7956c88cc5dbfbf50c08ae1e16746935a8db","schema_version":"1.0","event_id":"sha256:45d48c6a1a9a1e6a5b426f1b27cf7956c88cc5dbfbf50c08ae1e16746935a8db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LCMOD54RL7N5WUMM6WO6NZIEAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Refining Source Representations with Relation Networks for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiawei Hu, Qun Liu, Wen Zhang, Yang Feng","submitted_at":"2017-09-12T13:38:11Z","abstract_excerpt":"Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget old information which is often useful and the encoder only operates through words without considering word relationship. To solve these problems, we introduce a relation networks (RN) into NMT to refine the encoding representations of the source. In our method, the RN first augments the representation of each source word with its neighbors and reasons all the possible pairwise relations between them. Then the source r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03980","kind":"arxiv","version":3},"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":"2026-05-18T00:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b470nSU3kQlwni56CBTdh3GmGcol+yk62+msIV5w6hbhWxU7SnKXH5i9i/L1Aa/svgJEQ121d61lp+CRlAEsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:55:43.024152Z"},"content_sha256":"7b5c8c4e2d4ccbedd946e77bc9dfe90cb604f056575e36c4e6336009987b61ef","schema_version":"1.0","event_id":"sha256:7b5c8c4e2d4ccbedd946e77bc9dfe90cb604f056575e36c4e6336009987b61ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LCMOD54RL7N5WUMM6WO6NZIEAG/bundle.json","state_url":"https://pith.science/pith/LCMOD54RL7N5WUMM6WO6NZIEAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LCMOD54RL7N5WUMM6WO6NZIEAG/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":"2026-06-04T19:55:43Z","links":{"resolver":"https://pith.science/pith/LCMOD54RL7N5WUMM6WO6NZIEAG","bundle":"https://pith.science/pith/LCMOD54RL7N5WUMM6WO6NZIEAG/bundle.json","state":"https://pith.science/pith/LCMOD54RL7N5WUMM6WO6NZIEAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LCMOD54RL7N5WUMM6WO6NZIEAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LCMOD54RL7N5WUMM6WO6NZIEAG","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":"a1b9bf1e7f940cdcf4f7c99b1e35e8363bfbe640b523dbb960e2c2e686f723cf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T13:38:11Z","title_canon_sha256":"49f54a0e7b4b2e560d630c6183d1da2bce01e1923fc109b1599dad81201c8087"},"schema_version":"1.0","source":{"id":"1709.03980","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03980","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03980v3","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03980","created_at":"2026-05-18T00:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"LCMOD54RL7N5","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LCMOD54RL7N5WUMM","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LCMOD54R","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:7b5c8c4e2d4ccbedd946e77bc9dfe90cb604f056575e36c4e6336009987b61ef","target":"graph","created_at":"2026-05-18T00:14:59Z","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":"Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget old information which is often useful and the encoder only operates through words without considering word relationship. To solve these problems, we introduce a relation networks (RN) into NMT to refine the encoding representations of the source. In our method, the RN first augments the representation of each source word with its neighbors and reasons all the possible pairwise relations between them. Then the source r","authors_text":"Jiawei Hu, Qun Liu, Wen Zhang, Yang Feng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T13:38:11Z","title":"Refining Source Representations with Relation Networks for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03980","kind":"arxiv","version":3},"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":"sha256:45d48c6a1a9a1e6a5b426f1b27cf7956c88cc5dbfbf50c08ae1e16746935a8db","target":"record","created_at":"2026-05-18T00:14:59Z","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":"a1b9bf1e7f940cdcf4f7c99b1e35e8363bfbe640b523dbb960e2c2e686f723cf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-12T13:38:11Z","title_canon_sha256":"49f54a0e7b4b2e560d630c6183d1da2bce01e1923fc109b1599dad81201c8087"},"schema_version":"1.0","source":{"id":"1709.03980","kind":"arxiv","version":3}},"canonical_sha256":"5898e1f7915fdbdb518cf59de6e5040191ab39f5ad22752d41365792ca1b05be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5898e1f7915fdbdb518cf59de6e5040191ab39f5ad22752d41365792ca1b05be","first_computed_at":"2026-05-18T00:14:59.870026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:59.870026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0F6VKi9OkoJWLUoMMnx/BsSlh3CgVOYs+I59vgK0HKm3ua1z/3hbjk5FlCASavA/eX4z49f7tc/xMTLs5+sUDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:59.870677Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.03980","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45d48c6a1a9a1e6a5b426f1b27cf7956c88cc5dbfbf50c08ae1e16746935a8db","sha256:7b5c8c4e2d4ccbedd946e77bc9dfe90cb604f056575e36c4e6336009987b61ef"],"state_sha256":"23e471a5ffa3ad4a4670be5219ad8c91139ae70ac683ec28dca33b57e21744db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFKrcDivAmE4TIT2pEOgZUSN8tuo3B8Iqu1Ji2Dpd8YrErbLKkQBha2gopL6ej+5x60hDG5krI+eMj/sPKxOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T19:55:43.026115Z","bundle_sha256":"611449615ca9df7a18b937ae87bddd10930d1253c02d354cf03db7c67920e768"}}