{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GBJNSKTG7DLOXKZREXFNXINFMJ","short_pith_number":"pith:GBJNSKTG","schema_version":"1.0","canonical_sha256":"3052d92a66f8d6ebab3125cadba1a56267eedf307a79f8d42d498489765d0209","source":{"kind":"arxiv","id":"2410.22269","version":2},"attestation_state":"computed","paper":{"title":"Fourier Head: Helping Large Language Models Learn Complex Probability Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Sun, Daksh Aggarwal, Michael Freeman, Nate Gillman, Saurabh Singh","submitted_at":"2024-10-29T17:27:58Z","abstract_excerpt":"As the quality of large language models has improved, there has been increased interest in using them to model non-linguistic tokens. For example, the Decision Transformer recasts agentic decision making as a sequence modeling problem, using a decoder-only LLM to model the distribution over the discrete action space for an Atari agent. However, when adapting LLMs to non-linguistic domains, it remains unclear if softmax over discrete bins captures the continuous structure of the tokens and the potentially complex distributions needed for high quality token generation. We introduce a neural netw"},"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":"2410.22269","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T17:27:58Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"5cf81862e34387226f094d576c546361a8a4d10b675a3aacf6263aa8e8cc39e6","abstract_canon_sha256":"ec224498ec48920c5d43ee1b6c5995948dbe5ab2f3e68bd400e16872d2898834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:25.401467Z","signature_b64":"EMpAxBVwD1y5yiXwBaTp1q9NKsJHdEQnuBTzA9yOq2l3WLWgzrN7qcyEF85kEKtn7hW06cI0UMcuMXaLJRVxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3052d92a66f8d6ebab3125cadba1a56267eedf307a79f8d42d498489765d0209","last_reissued_at":"2026-07-05T10:28:25.400941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:25.400941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fourier Head: Helping Large Language Models Learn Complex Probability Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Sun, Daksh Aggarwal, Michael Freeman, Nate Gillman, Saurabh Singh","submitted_at":"2024-10-29T17:27:58Z","abstract_excerpt":"As the quality of large language models has improved, there has been increased interest in using them to model non-linguistic tokens. For example, the Decision Transformer recasts agentic decision making as a sequence modeling problem, using a decoder-only LLM to model the distribution over the discrete action space for an Atari agent. However, when adapting LLMs to non-linguistic domains, it remains unclear if softmax over discrete bins captures the continuous structure of the tokens and the potentially complex distributions needed for high quality token generation. We introduce a neural netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22269","kind":"arxiv","version":2},"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/2410.22269/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":"2410.22269","created_at":"2026-07-05T10:28:25.401004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22269v2","created_at":"2026-07-05T10:28:25.401004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22269","created_at":"2026-07-05T10:28:25.401004+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBJNSKTG7DLO","created_at":"2026-07-05T10:28:25.401004+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBJNSKTG7DLOXKZR","created_at":"2026-07-05T10:28:25.401004+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBJNSKTG","created_at":"2026-07-05T10:28:25.401004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17739","citing_title":"Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization","ref_index":2019,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ","json":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ.json","graph_json":"https://pith.science/api/pith-number/GBJNSKTG7DLOXKZREXFNXINFMJ/graph.json","events_json":"https://pith.science/api/pith-number/GBJNSKTG7DLOXKZREXFNXINFMJ/events.json","paper":"https://pith.science/paper/GBJNSKTG"},"agent_actions":{"view_html":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ","download_json":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ.json","view_paper":"https://pith.science/paper/GBJNSKTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22269&json=true","fetch_graph":"https://pith.science/api/pith-number/GBJNSKTG7DLOXKZREXFNXINFMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GBJNSKTG7DLOXKZREXFNXINFMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ/action/storage_attestation","attest_author":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ/action/author_attestation","sign_citation":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ/action/citation_signature","submit_replication":"https://pith.science/pith/GBJNSKTG7DLOXKZREXFNXINFMJ/action/replication_record"}},"created_at":"2026-07-05T10:28:25.401004+00:00","updated_at":"2026-07-05T10:28:25.401004+00:00"}