{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BA6MSQ5TSOLXANCBMJTCITCXCR","short_pith_number":"pith:BA6MSQ5T","schema_version":"1.0","canonical_sha256":"083cc943b393977034416266244c57147ee7df359c421c1ca8e16c07b6d8a785","source":{"kind":"arxiv","id":"2410.16703","version":1},"attestation_state":"computed","paper":{"title":"PLDR-LLM: Large Language Model from Power Law Decoder Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Burc Gokden","submitted_at":"2024-10-22T05:16:19Z","abstract_excerpt":"We present the Large Language Model from Power Law Decoder Representations (PLDR-LLM), a language model that leverages non-linear and linear transformations through Power Law Graph Attention mechanism to generate well-defined deductive and inductive outputs. We pretrain the PLDR-LLMs of varying layer sizes with a small batch size of 32 and $\\sim$8B tokens from the RefinedWeb dataset, and show that they achieve competitive performance in zero-shot and few-shot settings compared to scaled dot-product LLMs of similar model size reported in the literature. We show that deductive outputs of PLDR-LL"},"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":"2410.16703","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T05:16:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55050058e59bf40495cc4592f9235ad5c05a061a295738fa11d9d91e5d9b2ebf","abstract_canon_sha256":"3bc21468c1d3ae9c362fcfb6b4f4dfdba7879e8c32490a01889bd6b42ecc00f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:05.279637Z","signature_b64":"B6mAwhqZaYCGRm1Ii/qtGtzc+8sh/w6ejw4oX8C23ZGs1awMEb3GiW/L68b9SLqN4RlZ0FfAnH4nvm8zqDG/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"083cc943b393977034416266244c57147ee7df359c421c1ca8e16c07b6d8a785","last_reissued_at":"2026-07-05T09:24:05.278990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:05.278990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PLDR-LLM: Large Language Model from Power Law Decoder Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Burc Gokden","submitted_at":"2024-10-22T05:16:19Z","abstract_excerpt":"We present the Large Language Model from Power Law Decoder Representations (PLDR-LLM), a language model that leverages non-linear and linear transformations through Power Law Graph Attention mechanism to generate well-defined deductive and inductive outputs. We pretrain the PLDR-LLMs of varying layer sizes with a small batch size of 32 and $\\sim$8B tokens from the RefinedWeb dataset, and show that they achieve competitive performance in zero-shot and few-shot settings compared to scaled dot-product LLMs of similar model size reported in the literature. We show that deductive outputs of PLDR-LL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16703","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/2410.16703/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":"2410.16703","created_at":"2026-07-05T09:24:05.279054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16703v1","created_at":"2026-07-05T09:24:05.279054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16703","created_at":"2026-07-05T09:24:05.279054+00:00"},{"alias_kind":"pith_short_12","alias_value":"BA6MSQ5TSOLX","created_at":"2026-07-05T09:24:05.279054+00:00"},{"alias_kind":"pith_short_16","alias_value":"BA6MSQ5TSOLXANCB","created_at":"2026-07-05T09:24:05.279054+00:00"},{"alias_kind":"pith_short_8","alias_value":"BA6MSQ5T","created_at":"2026-07-05T09:24:05.279054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10288","citing_title":"Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR","json":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR.json","graph_json":"https://pith.science/api/pith-number/BA6MSQ5TSOLXANCBMJTCITCXCR/graph.json","events_json":"https://pith.science/api/pith-number/BA6MSQ5TSOLXANCBMJTCITCXCR/events.json","paper":"https://pith.science/paper/BA6MSQ5T"},"agent_actions":{"view_html":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR","download_json":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR.json","view_paper":"https://pith.science/paper/BA6MSQ5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16703&json=true","fetch_graph":"https://pith.science/api/pith-number/BA6MSQ5TSOLXANCBMJTCITCXCR/graph.json","fetch_events":"https://pith.science/api/pith-number/BA6MSQ5TSOLXANCBMJTCITCXCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR/action/storage_attestation","attest_author":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR/action/author_attestation","sign_citation":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR/action/citation_signature","submit_replication":"https://pith.science/pith/BA6MSQ5TSOLXANCBMJTCITCXCR/action/replication_record"}},"created_at":"2026-07-05T09:24:05.279054+00:00","updated_at":"2026-07-05T09:24:05.279054+00:00"}