{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XD6B4JEYL63DLMOFFEHHZUJKZR","short_pith_number":"pith:XD6B4JEY","schema_version":"1.0","canonical_sha256":"b8fc1e24985fb635b1c5290e7cd12acc51d19776e8cbf766bfcaf3cd2e082b6a","source":{"kind":"arxiv","id":"2408.00386","version":1},"attestation_state":"computed","paper":{"title":"What comes after transformers? -- A selective survey connecting ideas in deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Johannes Schneider","submitted_at":"2024-08-01T08:50:25Z","abstract_excerpt":"Transformers have become the de-facto standard model in artificial intelligence since 2017 despite numerous shortcomings ranging from energy inefficiency to hallucinations. Research has made a lot of progress in improving elements of transformers, and, more generally, deep learning manifesting in many proposals for architectures, layers, optimization objectives, and optimization techniques. For researchers it is difficult to keep track of such developments on a broader level. We provide a comprehensive overview of the many important, recent works in these areas to those who already have a basi"},"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":"2408.00386","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-01T08:50:25Z","cross_cats_sorted":[],"title_canon_sha256":"ea69eb7c590a95bf670b8e861ee8a20bdb37e32ced5a9973ac6878eb9c4b6504","abstract_canon_sha256":"7d340ef82c06fffb232906c6d33806dd1f882a303b17bc95342bbda2398849c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:02.935022Z","signature_b64":"0YOJNDUig0/qJoVny2bMpWpORBGVR7nZHUb7GkqIdbTriCFQY0zMnpeAQ9aQxIMtcbdlyL2glsTtcaHwIhPYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8fc1e24985fb635b1c5290e7cd12acc51d19776e8cbf766bfcaf3cd2e082b6a","last_reissued_at":"2026-07-05T08:51:02.934665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:02.934665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What comes after transformers? -- A selective survey connecting ideas in deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Johannes Schneider","submitted_at":"2024-08-01T08:50:25Z","abstract_excerpt":"Transformers have become the de-facto standard model in artificial intelligence since 2017 despite numerous shortcomings ranging from energy inefficiency to hallucinations. Research has made a lot of progress in improving elements of transformers, and, more generally, deep learning manifesting in many proposals for architectures, layers, optimization objectives, and optimization techniques. For researchers it is difficult to keep track of such developments on a broader level. We provide a comprehensive overview of the many important, recent works in these areas to those who already have a basi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00386","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/2408.00386/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":"2408.00386","created_at":"2026-07-05T08:51:02.934723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00386v1","created_at":"2026-07-05T08:51:02.934723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00386","created_at":"2026-07-05T08:51:02.934723+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD6B4JEYL63D","created_at":"2026-07-05T08:51:02.934723+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD6B4JEYL63DLMOF","created_at":"2026-07-05T08:51:02.934723+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD6B4JEY","created_at":"2026-07-05T08:51:02.934723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15661","citing_title":"Improving Next Tokens via Second-to-Last Predictions with Generate and Refine","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR","json":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR.json","graph_json":"https://pith.science/api/pith-number/XD6B4JEYL63DLMOFFEHHZUJKZR/graph.json","events_json":"https://pith.science/api/pith-number/XD6B4JEYL63DLMOFFEHHZUJKZR/events.json","paper":"https://pith.science/paper/XD6B4JEY"},"agent_actions":{"view_html":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR","download_json":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR.json","view_paper":"https://pith.science/paper/XD6B4JEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00386&json=true","fetch_graph":"https://pith.science/api/pith-number/XD6B4JEYL63DLMOFFEHHZUJKZR/graph.json","fetch_events":"https://pith.science/api/pith-number/XD6B4JEYL63DLMOFFEHHZUJKZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR/action/storage_attestation","attest_author":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR/action/author_attestation","sign_citation":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR/action/citation_signature","submit_replication":"https://pith.science/pith/XD6B4JEYL63DLMOFFEHHZUJKZR/action/replication_record"}},"created_at":"2026-07-05T08:51:02.934723+00:00","updated_at":"2026-07-05T08:51:02.934723+00:00"}