{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XOY6WI3LGMWZVLLWSNFHHKXLKL","short_pith_number":"pith:XOY6WI3L","schema_version":"1.0","canonical_sha256":"bbb1eb236b332d9aad76934a73aaeb52cf69f0e9dbf495abcd06bfa5959fae0a","source":{"kind":"arxiv","id":"2306.01070","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Attention Encoder Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Asier Mujika","submitted_at":"2023-06-01T18:17:23Z","abstract_excerpt":"Recent advances in large language models have shown that autoregressive modeling can generate complex and novel sequences that have many real-world applications. However, these models must generate outputs autoregressively, which becomes time-consuming when dealing with long sequences. Hierarchical autoregressive approaches that compress data have been proposed as a solution, but these methods still generate outputs at the original data frequency, resulting in slow and memory-intensive models. In this paper, we propose a model based on the Hierarchical Recurrent Encoder Decoder (HRED) architec"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.01070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T18:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"4fca7898f742419f34ec99981f60b054f3e048e632df3df5eb6ec7a24418707e","abstract_canon_sha256":"bec74c190fb1ea083d6ba2dd90e134de79a0e91d5a0f4e4680e7897828f26727"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:37.565544Z","signature_b64":"y4k0kmJoLm5+OMmqrkDKkyIx49zqiT2oEGpnkWIEPnwywpJI8x8xabsPbh+hQb8vfT5YKqjuioGEbUkd5j3gAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbb1eb236b332d9aad76934a73aaeb52cf69f0e9dbf495abcd06bfa5959fae0a","last_reissued_at":"2026-07-05T06:16:37.564919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:37.564919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Attention Encoder Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Asier Mujika","submitted_at":"2023-06-01T18:17:23Z","abstract_excerpt":"Recent advances in large language models have shown that autoregressive modeling can generate complex and novel sequences that have many real-world applications. However, these models must generate outputs autoregressively, which becomes time-consuming when dealing with long sequences. Hierarchical autoregressive approaches that compress data have been proposed as a solution, but these methods still generate outputs at the original data frequency, resulting in slow and memory-intensive models. In this paper, we propose a model based on the Hierarchical Recurrent Encoder Decoder (HRED) architec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01070","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.01070/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.01070","created_at":"2026-07-05T06:16:37.565000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01070v1","created_at":"2026-07-05T06:16:37.565000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01070","created_at":"2026-07-05T06:16:37.565000+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOY6WI3LGMWZ","created_at":"2026-07-05T06:16:37.565000+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOY6WI3LGMWZVLLW","created_at":"2026-07-05T06:16:37.565000+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOY6WI3L","created_at":"2026-07-05T06:16:37.565000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09604","citing_title":"SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL","json":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL.json","graph_json":"https://pith.science/api/pith-number/XOY6WI3LGMWZVLLWSNFHHKXLKL/graph.json","events_json":"https://pith.science/api/pith-number/XOY6WI3LGMWZVLLWSNFHHKXLKL/events.json","paper":"https://pith.science/paper/XOY6WI3L"},"agent_actions":{"view_html":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL","download_json":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL.json","view_paper":"https://pith.science/paper/XOY6WI3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01070&json=true","fetch_graph":"https://pith.science/api/pith-number/XOY6WI3LGMWZVLLWSNFHHKXLKL/graph.json","fetch_events":"https://pith.science/api/pith-number/XOY6WI3LGMWZVLLWSNFHHKXLKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL/action/storage_attestation","attest_author":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL/action/author_attestation","sign_citation":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL/action/citation_signature","submit_replication":"https://pith.science/pith/XOY6WI3LGMWZVLLWSNFHHKXLKL/action/replication_record"}},"created_at":"2026-07-05T06:16:37.565000+00:00","updated_at":"2026-07-05T06:16:37.565000+00:00"}