{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BLAWLMHVLCZOJGMXUP43NI3IGP","short_pith_number":"pith:BLAWLMHV","canonical_record":{"source":{"id":"2402.11417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T01:20:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c5dd3945ec7d753227187d1291d075970eb3144d223d059e975000b329307d77","abstract_canon_sha256":"bccec6821d0629a96feb02b0e0829d443cd83e5a71c407ef866130de2ab8a520"},"schema_version":"1.0"},"canonical_sha256":"0ac165b0f558b2e49997a3f9b6a36833d62892abf69007bfee380784d2c37d1b","source":{"kind":"arxiv","id":"2402.11417","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11417","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11417v1","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11417","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"BLAWLMHVLCZO","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"BLAWLMHVLCZOJGMX","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"BLAWLMHV","created_at":"2026-07-05T07:46:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BLAWLMHVLCZOJGMXUP43NI3IGP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T01:20:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c5dd3945ec7d753227187d1291d075970eb3144d223d059e975000b329307d77","abstract_canon_sha256":"bccec6821d0629a96feb02b0e0829d443cd83e5a71c407ef866130de2ab8a520"},"schema_version":"1.0"},"canonical_sha256":"0ac165b0f558b2e49997a3f9b6a36833d62892abf69007bfee380784d2c37d1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:38.814461Z","signature_b64":"S5ck+3UcglDkdVE8st9s7EgDQQ3YNSFoVFpCmcB9up+zwHLI08VIqrLgyUef/5kjmgJ5AV7XooHYfr8YRnz5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ac165b0f558b2e49997a3f9b6a36833d62892abf69007bfee380784d2c37d1b","last_reissued_at":"2026-07-05T07:46:38.813982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:38.813982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11417","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:46:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8LHK56xllfJxIn5vc1ztAPXtPtZ9NOy4xfMMnU0NsGby5zZsmpet73JjdFOJjWaTOilq07YZpYfFleFHitNtDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:23:56.443995Z"},"content_sha256":"635820498f6f9bcab474fdd65cc678a7a4eeac10e70f0dd8da598feccbab4e34","schema_version":"1.0","event_id":"sha256:635820498f6f9bcab474fdd65cc678a7a4eeac10e70f0dd8da598feccbab4e34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BLAWLMHVLCZOJGMXUP43NI3IGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiajun Zhou, Ngai Wong, Yifan Yang, Zheng Zhang","submitted_at":"2024-02-18T01:20:00Z","abstract_excerpt":"Various parameter-efficient fine-tuning (PEFT) techniques have been proposed to enable computationally efficient fine-tuning while maintaining model performance. However, existing PEFT methods are still limited by the growing number of trainable parameters with the rapid deployment of Large Language Models (LLMs). To address this challenge, we present LoRETTA, an ultra-parameter-efficient framework that significantly reduces trainable parameters through tensor-train decomposition. Specifically, we propose two methods, named {LoRETTA}$_{adp}$ and {LoRETTA}$_{rep}$. The former employs tensorized"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11417","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/2402.11417/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:46:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u2tUNvcb1XccufHCD/9aX/nI0KSzBrKc+Y7iAw7tFAqHg+G6Dl0TOPON4jqAQuAksJHPWWqXbR6tyRNiEZXKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:23:56.444591Z"},"content_sha256":"529bf2718bd1e78ce076e956befb3c32b18a255c9231ad1e59db49828ce153fb","schema_version":"1.0","event_id":"sha256:529bf2718bd1e78ce076e956befb3c32b18a255c9231ad1e59db49828ce153fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLAWLMHVLCZOJGMXUP43NI3IGP/bundle.json","state_url":"https://pith.science/pith/BLAWLMHVLCZOJGMXUP43NI3IGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLAWLMHVLCZOJGMXUP43NI3IGP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T15:23:56Z","links":{"resolver":"https://pith.science/pith/BLAWLMHVLCZOJGMXUP43NI3IGP","bundle":"https://pith.science/pith/BLAWLMHVLCZOJGMXUP43NI3IGP/bundle.json","state":"https://pith.science/pith/BLAWLMHVLCZOJGMXUP43NI3IGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLAWLMHVLCZOJGMXUP43NI3IGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BLAWLMHVLCZOJGMXUP43NI3IGP","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":"bccec6821d0629a96feb02b0e0829d443cd83e5a71c407ef866130de2ab8a520","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T01:20:00Z","title_canon_sha256":"c5dd3945ec7d753227187d1291d075970eb3144d223d059e975000b329307d77"},"schema_version":"1.0","source":{"id":"2402.11417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11417","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11417v1","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11417","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"BLAWLMHVLCZO","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"BLAWLMHVLCZOJGMX","created_at":"2026-07-05T07:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"BLAWLMHV","created_at":"2026-07-05T07:46:38Z"}],"graph_snapshots":[{"event_id":"sha256:529bf2718bd1e78ce076e956befb3c32b18a255c9231ad1e59db49828ce153fb","target":"graph","created_at":"2026-07-05T07:46:38Z","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/2402.11417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Various parameter-efficient fine-tuning (PEFT) techniques have been proposed to enable computationally efficient fine-tuning while maintaining model performance. However, existing PEFT methods are still limited by the growing number of trainable parameters with the rapid deployment of Large Language Models (LLMs). To address this challenge, we present LoRETTA, an ultra-parameter-efficient framework that significantly reduces trainable parameters through tensor-train decomposition. Specifically, we propose two methods, named {LoRETTA}$_{adp}$ and {LoRETTA}$_{rep}$. The former employs tensorized","authors_text":"Jiajun Zhou, Ngai Wong, Yifan Yang, Zheng Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T01:20:00Z","title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11417","kind":"arxiv","version":1},"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":"sha256:635820498f6f9bcab474fdd65cc678a7a4eeac10e70f0dd8da598feccbab4e34","target":"record","created_at":"2026-07-05T07:46:38Z","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":"bccec6821d0629a96feb02b0e0829d443cd83e5a71c407ef866130de2ab8a520","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T01:20:00Z","title_canon_sha256":"c5dd3945ec7d753227187d1291d075970eb3144d223d059e975000b329307d77"},"schema_version":"1.0","source":{"id":"2402.11417","kind":"arxiv","version":1}},"canonical_sha256":"0ac165b0f558b2e49997a3f9b6a36833d62892abf69007bfee380784d2c37d1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ac165b0f558b2e49997a3f9b6a36833d62892abf69007bfee380784d2c37d1b","first_computed_at":"2026-07-05T07:46:38.813982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:38.813982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S5ck+3UcglDkdVE8st9s7EgDQQ3YNSFoVFpCmcB9up+zwHLI08VIqrLgyUef/5kjmgJ5AV7XooHYfr8YRnz5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:38.814461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:635820498f6f9bcab474fdd65cc678a7a4eeac10e70f0dd8da598feccbab4e34","sha256:529bf2718bd1e78ce076e956befb3c32b18a255c9231ad1e59db49828ce153fb"],"state_sha256":"5440041b83a911e9c885fef6c062ef84d53f94769093844c2535155f755edd4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jSfzQpoWs1hmh0VP7J9EFT7glawHGkBJLdI93s6592vkF+8BEH5gHZQ5Qhtq8nyjG7JDShC54mstsHnyyG/VAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:23:56.449549Z","bundle_sha256":"27ad138bf0f612079ed5884000e7bf26b913eaa1e07259f3d9b7586bdb0ec6d3"}}