{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5XTGLNMH46235C2R6KVUS7D44D","short_pith_number":"pith:5XTGLNMH","canonical_record":{"source":{"id":"1801.09797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T23:36:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94aec9e433596f169d4e07e9b6d23a62f521ba123cdc59ad1e51a917a36630c3","abstract_canon_sha256":"e98e1ab4238e95e7fd510e8af23bfb2ca002da5ed562fb35d19cfef7cbe8293f"},"schema_version":"1.0"},"canonical_sha256":"ede665b587e7b5be8b51f2ab497c7ce0ceb430cf3f4615b6f7e95651009650ef","source":{"kind":"arxiv","id":"1801.09797","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09797","created_at":"2026-05-18T00:24:46Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09797v1","created_at":"2026-05-18T00:24:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09797","created_at":"2026-05-18T00:24:46Z"},{"alias_kind":"pith_short_12","alias_value":"5XTGLNMH4623","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5XTGLNMH46235C2R","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5XTGLNMH","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5XTGLNMH46235C2R6KVUS7D44D","target":"record","payload":{"canonical_record":{"source":{"id":"1801.09797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T23:36:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94aec9e433596f169d4e07e9b6d23a62f521ba123cdc59ad1e51a917a36630c3","abstract_canon_sha256":"e98e1ab4238e95e7fd510e8af23bfb2ca002da5ed562fb35d19cfef7cbe8293f"},"schema_version":"1.0"},"canonical_sha256":"ede665b587e7b5be8b51f2ab497c7ce0ceb430cf3f4615b6f7e95651009650ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:46.635439Z","signature_b64":"NWkre2McS1zBPUIX6wWeIfp91A2NWMzYRq0oAm4pMzk1QKOW9MmHwTfYHAQSxW+ga49k3zSArs0ELzcDR2NmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ede665b587e7b5be8b51f2ab497c7ce0ceb430cf3f4615b6f7e95651009650ef","last_reissued_at":"2026-05-18T00:24:46.634784Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:46.634784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.09797","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":"2026-05-18T00:24:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2upbvw1K2JT6EDsnFsTkmvhz1j2NZI0+2B34dLmah0RDb8HWIuuIEirbPS6sGJQ/JjuUvjzc3kMQORJScWwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:37:36.882824Z"},"content_sha256":"aa7e6792f65e26c2914b7b68f8c6d1748041910d33b83818c94c4335af62a90c","schema_version":"1.0","event_id":"sha256:aa7e6792f65e26c2914b7b68f8c6d1748041910d33b83818c94c4335af62a90c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5XTGLNMH46235C2R6KVUS7D44D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrete Autoencoders for Sequence Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"{\\L}ukasz Kaiser, Samy Bengio","submitted_at":"2018-01-29T23:36:11Z","abstract_excerpt":"Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters through words to sentences, it is not apparent in current language models. We propose to improve the representation in sequence models by augmenting current approaches with an autoencoder that is forced to compress the sequence through an intermediate discrete latent space. In order to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09797","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":"2026-05-18T00:24:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j3cFYHx3U1gGyx6YTtKI9y+cVy3gwcxle2UF6eP5UK3PKkopwqKftkAFGtaM86rXIe13m7AW37Eby7xd2I25Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:37:36.883172Z"},"content_sha256":"0296d931acc6365016d786875715a91026470aa909715192941d75bf4258e6e9","schema_version":"1.0","event_id":"sha256:0296d931acc6365016d786875715a91026470aa909715192941d75bf4258e6e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XTGLNMH46235C2R6KVUS7D44D/bundle.json","state_url":"https://pith.science/pith/5XTGLNMH46235C2R6KVUS7D44D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XTGLNMH46235C2R6KVUS7D44D/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":"2026-06-02T21:37:36Z","links":{"resolver":"https://pith.science/pith/5XTGLNMH46235C2R6KVUS7D44D","bundle":"https://pith.science/pith/5XTGLNMH46235C2R6KVUS7D44D/bundle.json","state":"https://pith.science/pith/5XTGLNMH46235C2R6KVUS7D44D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XTGLNMH46235C2R6KVUS7D44D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5XTGLNMH46235C2R6KVUS7D44D","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":"e98e1ab4238e95e7fd510e8af23bfb2ca002da5ed562fb35d19cfef7cbe8293f","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T23:36:11Z","title_canon_sha256":"94aec9e433596f169d4e07e9b6d23a62f521ba123cdc59ad1e51a917a36630c3"},"schema_version":"1.0","source":{"id":"1801.09797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09797","created_at":"2026-05-18T00:24:46Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09797v1","created_at":"2026-05-18T00:24:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09797","created_at":"2026-05-18T00:24:46Z"},{"alias_kind":"pith_short_12","alias_value":"5XTGLNMH4623","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5XTGLNMH46235C2R","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5XTGLNMH","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:0296d931acc6365016d786875715a91026470aa909715192941d75bf4258e6e9","target":"graph","created_at":"2026-05-18T00:24:46Z","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":"Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters through words to sentences, it is not apparent in current language models. We propose to improve the representation in sequence models by augmenting current approaches with an autoencoder that is forced to compress the sequence through an intermediate discrete latent space. In order to","authors_text":"{\\L}ukasz Kaiser, Samy Bengio","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T23:36:11Z","title":"Discrete Autoencoders for Sequence Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09797","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:aa7e6792f65e26c2914b7b68f8c6d1748041910d33b83818c94c4335af62a90c","target":"record","created_at":"2026-05-18T00:24:46Z","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":"e98e1ab4238e95e7fd510e8af23bfb2ca002da5ed562fb35d19cfef7cbe8293f","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-01-29T23:36:11Z","title_canon_sha256":"94aec9e433596f169d4e07e9b6d23a62f521ba123cdc59ad1e51a917a36630c3"},"schema_version":"1.0","source":{"id":"1801.09797","kind":"arxiv","version":1}},"canonical_sha256":"ede665b587e7b5be8b51f2ab497c7ce0ceb430cf3f4615b6f7e95651009650ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ede665b587e7b5be8b51f2ab497c7ce0ceb430cf3f4615b6f7e95651009650ef","first_computed_at":"2026-05-18T00:24:46.634784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:46.634784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NWkre2McS1zBPUIX6wWeIfp91A2NWMzYRq0oAm4pMzk1QKOW9MmHwTfYHAQSxW+ga49k3zSArs0ELzcDR2NmBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:46.635439Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.09797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa7e6792f65e26c2914b7b68f8c6d1748041910d33b83818c94c4335af62a90c","sha256:0296d931acc6365016d786875715a91026470aa909715192941d75bf4258e6e9"],"state_sha256":"485313a1663ef44efeed551d0aecac5b27802c94cec0f13777a1b0b7935a7411"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sl7RmQ9z7B5TqxDqU9aH+XFx/Mu+1xBy2twDsoZYoH3EVflgwzoQb8CobnbhvSM/5YIaB0axzyN8/FodJ5dUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:37:36.885116Z","bundle_sha256":"cbe61960534158c1316b5d9c62820242069defe0a94dcb8e9a20bb86bbec2d18"}}