{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SFR52VHZXNODG3SGEQJDIDPQ2C","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":"0750a3df8bbd3a50b5c1c9dca49feb177f3635d4f3c74d0bdfdd5c6b072253e2","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2024-09-04T03:17:19Z","title_canon_sha256":"34047c43c1041d1d9405f6d84428b05db9210984cdc41256a49ad7e782a0a531"},"schema_version":"1.0","source":{"id":"2409.12924","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12924","created_at":"2026-07-05T10:11:24Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12924v4","created_at":"2026-07-05T10:11:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12924","created_at":"2026-07-05T10:11:24Z"},{"alias_kind":"pith_short_12","alias_value":"SFR52VHZXNOD","created_at":"2026-07-05T10:11:24Z"},{"alias_kind":"pith_short_16","alias_value":"SFR52VHZXNODG3SG","created_at":"2026-07-05T10:11:24Z"},{"alias_kind":"pith_short_8","alias_value":"SFR52VHZ","created_at":"2026-07-05T10:11:24Z"}],"graph_snapshots":[{"event_id":"sha256:27471ffcd96e0336681eb5b710f1c4593510969d8e6a4267ca566aa4caed50b8","target":"graph","created_at":"2026-07-05T10:11:24Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.12924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have ushered in a new wave of artificial intelligence advancements impacting every scientific field and discipline. We live in a world where most of the data around us, e.g., text, audio, and music, has a multi-scale structure. This paper infuses LLMs with a traditional signal processing idea, namely wavelets, during pre-training to take advantage of the structure. Without adding \\textbf{any extra parameters} to a GPT-style LLM architecture in an academic setup, we achieve the same pre-training performance almost twice as fast in text, audio, and images. This is do","authors_text":"Prateek Verma","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2024-09-04T03:17:19Z","title":"Wavelet GPT: Wavelet Inspired Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12924","kind":"arxiv","version":4},"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":"sha256:6e6cb9eb65aac60576e25a625c2f912903a6062192e6cc37f313218bb5cc22b3","target":"record","created_at":"2026-07-05T10:11:24Z","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":"0750a3df8bbd3a50b5c1c9dca49feb177f3635d4f3c74d0bdfdd5c6b072253e2","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2024-09-04T03:17:19Z","title_canon_sha256":"34047c43c1041d1d9405f6d84428b05db9210984cdc41256a49ad7e782a0a531"},"schema_version":"1.0","source":{"id":"2409.12924","kind":"arxiv","version":4}},"canonical_sha256":"9163dd54f9bb5c336e462412340df0d0b4091eb194d25d79aeef4ad5df276167","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9163dd54f9bb5c336e462412340df0d0b4091eb194d25d79aeef4ad5df276167","first_computed_at":"2026-07-05T10:11:24.446452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:24.446452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fiJBIR1YV/XlykSQNA0iWEXKUUWFhPF2n4f5VtLiQUOfx8/qJm8kZLkiQLA6OobP/uTdH4oZqsfH6c+CLBadCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:24.447026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12924","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e6cb9eb65aac60576e25a625c2f912903a6062192e6cc37f313218bb5cc22b3","sha256:27471ffcd96e0336681eb5b710f1c4593510969d8e6a4267ca566aa4caed50b8"],"state_sha256":"af0e7753e7366fc7c1c41c94c34ad8a0549a544c6f1892dfbcbaa318303120bb"}