{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BZE5GNODGOYEG43IQ6JCFPCCHM","short_pith_number":"pith:BZE5GNOD","canonical_record":{"source":{"id":"1708.04729","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-16T00:52:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fee14d0bdd873b6775dd11ebb4bc4e7bed61c6905010d39566ea55a0e09b302f","abstract_canon_sha256":"d0c5bbf8dafba26e05fba2b7bb81f3d646666130c3ebba76fc32218a65c630ff"},"schema_version":"1.0"},"canonical_sha256":"0e49d335c333b0437368879222bc423b2a19552a26373792eb63a783857e347c","source":{"kind":"arxiv","id":"1708.04729","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04729","created_at":"2026-05-18T00:34:34Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04729v3","created_at":"2026-05-18T00:34:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04729","created_at":"2026-05-18T00:34:34Z"},{"alias_kind":"pith_short_12","alias_value":"BZE5GNODGOYE","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BZE5GNODGOYEG43I","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BZE5GNOD","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BZE5GNODGOYEG43IQ6JCFPCCHM","target":"record","payload":{"canonical_record":{"source":{"id":"1708.04729","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-16T00:52:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fee14d0bdd873b6775dd11ebb4bc4e7bed61c6905010d39566ea55a0e09b302f","abstract_canon_sha256":"d0c5bbf8dafba26e05fba2b7bb81f3d646666130c3ebba76fc32218a65c630ff"},"schema_version":"1.0"},"canonical_sha256":"0e49d335c333b0437368879222bc423b2a19552a26373792eb63a783857e347c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:34.781088Z","signature_b64":"SChzbiOCNbFRDwWxHmkG1ORwMTvGzLPBz/pn1S+VAYBKlT0tZyF5Dn6pgr+d7clNtR+klXP9YRkXv27mt44FAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e49d335c333b0437368879222bc423b2a19552a26373792eb63a783857e347c","last_reissued_at":"2026-05-18T00:34:34.780584Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:34.780584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.04729","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":"2026-05-18T00:34:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ox1cV8vJ9BsJEnLq/2y3IWkjidZQaT/SC2NcVvx4sO9Wyu+wu8E+2Sz7Lpi8ELX8aZGncOyN/HdcQkyN31pJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:18:09.326279Z"},"content_sha256":"535a9843dd5ff170caa324f22bdcc2d2cb5acc97828200d73cb326fc8dd5a83e","schema_version":"1.0","event_id":"sha256:535a9843dd5ff170caa324f22bdcc2d2cb5acc97828200d73cb326fc8dd5a83e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BZE5GNODGOYEG43IQ6JCFPCCHM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deconvolutional Paragraph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Dinghan Shen, Guoyin Wang, Lawrence Carin, Ricardo Henao, Yizhe Zhang, Zhe Gan","submitted_at":"2017-08-16T00:52:32Z","abstract_excerpt":"Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the length of the text. We propose a sequence-to-sequence, purely convolutional and deconvolutional autoencoding framework that is free of the above issue, while also being computationally efficient. The proposed method is simple, easy to implement and can be leveraged as a building bloc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04729","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":"2026-05-18T00:34:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQiD0T0Ld6enxI8EGUXe+e/3S9NU0owwAR0f5Tia2bD9GAQV/Sr6CLrPy/ng6Vwr/SjcEtfdZV7USykJ8OaACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:18:09.326825Z"},"content_sha256":"0822fdb3dd15dfdf27a49f54d5ac573738763faa561466a5aefacce63eb05f34","schema_version":"1.0","event_id":"sha256:0822fdb3dd15dfdf27a49f54d5ac573738763faa561466a5aefacce63eb05f34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZE5GNODGOYEG43IQ6JCFPCCHM/bundle.json","state_url":"https://pith.science/pith/BZE5GNODGOYEG43IQ6JCFPCCHM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZE5GNODGOYEG43IQ6JCFPCCHM/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":"2026-05-26T23:18:09Z","links":{"resolver":"https://pith.science/pith/BZE5GNODGOYEG43IQ6JCFPCCHM","bundle":"https://pith.science/pith/BZE5GNODGOYEG43IQ6JCFPCCHM/bundle.json","state":"https://pith.science/pith/BZE5GNODGOYEG43IQ6JCFPCCHM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZE5GNODGOYEG43IQ6JCFPCCHM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BZE5GNODGOYEG43IQ6JCFPCCHM","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":"d0c5bbf8dafba26e05fba2b7bb81f3d646666130c3ebba76fc32218a65c630ff","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-16T00:52:32Z","title_canon_sha256":"fee14d0bdd873b6775dd11ebb4bc4e7bed61c6905010d39566ea55a0e09b302f"},"schema_version":"1.0","source":{"id":"1708.04729","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04729","created_at":"2026-05-18T00:34:34Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04729v3","created_at":"2026-05-18T00:34:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04729","created_at":"2026-05-18T00:34:34Z"},{"alias_kind":"pith_short_12","alias_value":"BZE5GNODGOYE","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BZE5GNODGOYEG43I","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BZE5GNOD","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:0822fdb3dd15dfdf27a49f54d5ac573738763faa561466a5aefacce63eb05f34","target":"graph","created_at":"2026-05-18T00:34:34Z","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":"Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the length of the text. We propose a sequence-to-sequence, purely convolutional and deconvolutional autoencoding framework that is free of the above issue, while also being computationally efficient. The proposed method is simple, easy to implement and can be leveraged as a building bloc","authors_text":"Dinghan Shen, Guoyin Wang, Lawrence Carin, Ricardo Henao, Yizhe Zhang, Zhe Gan","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-16T00:52:32Z","title":"Deconvolutional Paragraph Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04729","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":"sha256:535a9843dd5ff170caa324f22bdcc2d2cb5acc97828200d73cb326fc8dd5a83e","target":"record","created_at":"2026-05-18T00:34:34Z","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":"d0c5bbf8dafba26e05fba2b7bb81f3d646666130c3ebba76fc32218a65c630ff","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-16T00:52:32Z","title_canon_sha256":"fee14d0bdd873b6775dd11ebb4bc4e7bed61c6905010d39566ea55a0e09b302f"},"schema_version":"1.0","source":{"id":"1708.04729","kind":"arxiv","version":3}},"canonical_sha256":"0e49d335c333b0437368879222bc423b2a19552a26373792eb63a783857e347c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e49d335c333b0437368879222bc423b2a19552a26373792eb63a783857e347c","first_computed_at":"2026-05-18T00:34:34.780584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:34.780584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SChzbiOCNbFRDwWxHmkG1ORwMTvGzLPBz/pn1S+VAYBKlT0tZyF5Dn6pgr+d7clNtR+klXP9YRkXv27mt44FAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:34.781088Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.04729","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:535a9843dd5ff170caa324f22bdcc2d2cb5acc97828200d73cb326fc8dd5a83e","sha256:0822fdb3dd15dfdf27a49f54d5ac573738763faa561466a5aefacce63eb05f34"],"state_sha256":"9533a845d0d927c2f50045ddc163bd97a37d351d53ad5731eb6ee4a4f33e8d1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14jl6JJ/JFBbEmRaCB7R5YRvzJO7Vdg6q62FBXEZY2IcqTqUKgW8ZPR/QYHb8JY53k+I+71561+vfZ5cZYItAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:18:09.329222Z","bundle_sha256":"88d449e166952a1a0911e2038046238ba4d091f3b3fe68833231d0cde975ab2a"}}