{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AGPOFE3LVJSKJSXKAOUZRF4XPN","short_pith_number":"pith:AGPOFE3L","canonical_record":{"source":{"id":"1808.08003","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T05:00:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f2d27d6869452255104969cbfb6ec6622932eeb195a92689de2598750762ad7","abstract_canon_sha256":"5fc04cf3efbab2a0c12558b406a4afeff110d7c967391c12a605e7e3cae6a90c"},"schema_version":"1.0"},"canonical_sha256":"019ee2936baa64a4caea03a99897977b741d2059e412ab830c16cb36b180c79b","source":{"kind":"arxiv","id":"1808.08003","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08003","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08003v3","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08003","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"AGPOFE3LVJSK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AGPOFE3LVJSKJSXK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AGPOFE3L","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AGPOFE3LVJSKJSXKAOUZRF4XPN","target":"record","payload":{"canonical_record":{"source":{"id":"1808.08003","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T05:00:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f2d27d6869452255104969cbfb6ec6622932eeb195a92689de2598750762ad7","abstract_canon_sha256":"5fc04cf3efbab2a0c12558b406a4afeff110d7c967391c12a605e7e3cae6a90c"},"schema_version":"1.0"},"canonical_sha256":"019ee2936baa64a4caea03a99897977b741d2059e412ab830c16cb36b180c79b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:36.818790Z","signature_b64":"Ijo2PhxOBQ1Vl4eHEiKXY9Mw3UnPzzkc+ZgqSPPlzkMwug6+x6WLRHxcVw7y9S3cb5MYJPAQYPLDqvlAp30aCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"019ee2936baa64a4caea03a99897977b741d2059e412ab830c16cb36b180c79b","last_reissued_at":"2026-05-18T00:06:36.818308Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:36.818308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.08003","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":"2026-05-18T00:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hU0BA/t6Mcb0nMhR5g3f44j7wxEP1+zotsL+2MQM2IpSCVXb6lftDD4QzcQlHjLTQBJrK+p+wp+AyDlRvFIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:38:12.428011Z"},"content_sha256":"0d350beb6ee89567e063685c1527dc86be0381a4465aaa77763bebcedaaa9443","schema_version":"1.0","event_id":"sha256:0d350beb6ee89567e063685c1527dc86be0381a4465aaa77763bebcedaaa9443"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AGPOFE3LVJSKJSXKAOUZRF4XPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Distribution Matching for Sequence-to-Sequence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guanlin Li, Ming Zhou, Mu Li, Shujie Liu, Wenhu Chen, Zhirui Zhang","submitted_at":"2018-08-24T05:00:17Z","abstract_excerpt":"Sequence-to-Sequence models were introduced to tackle many real-life problems like machine translation, summarization, image captioning, etc. The standard optimization algorithms are mainly based on example-to-example matching like maximum likelihood estimation, which is known to suffer from data sparsity problem. Here we present an alternate view to explain sequence-to-sequence learning as a distribution matching problem, where each source or target example is viewed to represent a local latent distribution in the source or target domain. Then, we interpret sequence-to-sequence learning as le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08003","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":"2026-05-18T00:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pSy/wRBHxyAgOntfV2gaLmUruW2nvPf46hTN+Jtlk2mFQOmxUByAUqrdRx0L+o7l0JOWO0eodYJ7PqaRwfKeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:38:12.428754Z"},"content_sha256":"c60143e05b93e2dda7c93808ea0e897b10e866f0bb675a510598d389e677016a","schema_version":"1.0","event_id":"sha256:c60143e05b93e2dda7c93808ea0e897b10e866f0bb675a510598d389e677016a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGPOFE3LVJSKJSXKAOUZRF4XPN/bundle.json","state_url":"https://pith.science/pith/AGPOFE3LVJSKJSXKAOUZRF4XPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGPOFE3LVJSKJSXKAOUZRF4XPN/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":"2026-05-25T16:38:12Z","links":{"resolver":"https://pith.science/pith/AGPOFE3LVJSKJSXKAOUZRF4XPN","bundle":"https://pith.science/pith/AGPOFE3LVJSKJSXKAOUZRF4XPN/bundle.json","state":"https://pith.science/pith/AGPOFE3LVJSKJSXKAOUZRF4XPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGPOFE3LVJSKJSXKAOUZRF4XPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AGPOFE3LVJSKJSXKAOUZRF4XPN","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":"5fc04cf3efbab2a0c12558b406a4afeff110d7c967391c12a605e7e3cae6a90c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T05:00:17Z","title_canon_sha256":"8f2d27d6869452255104969cbfb6ec6622932eeb195a92689de2598750762ad7"},"schema_version":"1.0","source":{"id":"1808.08003","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08003","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08003v3","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08003","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"AGPOFE3LVJSK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AGPOFE3LVJSKJSXK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AGPOFE3L","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:c60143e05b93e2dda7c93808ea0e897b10e866f0bb675a510598d389e677016a","target":"graph","created_at":"2026-05-18T00:06:36Z","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":"Sequence-to-Sequence models were introduced to tackle many real-life problems like machine translation, summarization, image captioning, etc. The standard optimization algorithms are mainly based on example-to-example matching like maximum likelihood estimation, which is known to suffer from data sparsity problem. Here we present an alternate view to explain sequence-to-sequence learning as a distribution matching problem, where each source or target example is viewed to represent a local latent distribution in the source or target domain. Then, we interpret sequence-to-sequence learning as le","authors_text":"Guanlin Li, Ming Zhou, Mu Li, Shujie Liu, Wenhu Chen, Zhirui Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T05:00:17Z","title":"Approximate Distribution Matching for Sequence-to-Sequence Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08003","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":"sha256:0d350beb6ee89567e063685c1527dc86be0381a4465aaa77763bebcedaaa9443","target":"record","created_at":"2026-05-18T00:06:36Z","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":"5fc04cf3efbab2a0c12558b406a4afeff110d7c967391c12a605e7e3cae6a90c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T05:00:17Z","title_canon_sha256":"8f2d27d6869452255104969cbfb6ec6622932eeb195a92689de2598750762ad7"},"schema_version":"1.0","source":{"id":"1808.08003","kind":"arxiv","version":3}},"canonical_sha256":"019ee2936baa64a4caea03a99897977b741d2059e412ab830c16cb36b180c79b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"019ee2936baa64a4caea03a99897977b741d2059e412ab830c16cb36b180c79b","first_computed_at":"2026-05-18T00:06:36.818308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:36.818308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ijo2PhxOBQ1Vl4eHEiKXY9Mw3UnPzzkc+ZgqSPPlzkMwug6+x6WLRHxcVw7y9S3cb5MYJPAQYPLDqvlAp30aCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:36.818790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.08003","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d350beb6ee89567e063685c1527dc86be0381a4465aaa77763bebcedaaa9443","sha256:c60143e05b93e2dda7c93808ea0e897b10e866f0bb675a510598d389e677016a"],"state_sha256":"2e382b748f6df31e58676571778fdd447f61ac3e936fc4b497a9e056ac76daa8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uGJitUbbJGXuLcUFinGkEED0pehMVKJl7r+I1fSpa3J8GwS8J61OABhfR/PzbbDIE54AXgsNEnwSjk6oFN0TAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:38:12.432540Z","bundle_sha256":"b5fc572f095f16799df5d0c1b89226327e8c07f82b38308c567600252002e839"}}