{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GV2PW525QTBPMSQZYH6TNJEM7T","short_pith_number":"pith:GV2PW525","canonical_record":{"source":{"id":"2506.16456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T16:46:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"61197f9241c0f7781e22ea27966bcc062f86bbab4ed6d2fbdc588e20c33086c5","abstract_canon_sha256":"2a2c14f785c2e77c07b8b3b61753538d7853109ce052da7f79985a7aded0b836"},"schema_version":"1.0"},"canonical_sha256":"3574fb775d84c2f64a19c1fd36a48cfcf863bf4a93a09a99259e4bb938235dbb","source":{"kind":"arxiv","id":"2506.16456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16456","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16456v1","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16456","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"GV2PW525QTBP","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_16","alias_value":"GV2PW525QTBPMSQZ","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_8","alias_value":"GV2PW525","created_at":"2026-07-05T11:24:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GV2PW525QTBPMSQZYH6TNJEM7T","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T16:46:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"61197f9241c0f7781e22ea27966bcc062f86bbab4ed6d2fbdc588e20c33086c5","abstract_canon_sha256":"2a2c14f785c2e77c07b8b3b61753538d7853109ce052da7f79985a7aded0b836"},"schema_version":"1.0"},"canonical_sha256":"3574fb775d84c2f64a19c1fd36a48cfcf863bf4a93a09a99259e4bb938235dbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:36.771715Z","signature_b64":"DuTBIcqs0c55tO5uRBM/fI9FW4PsjyKLPw51kI83L7yLYynuq+zXxwNrnrl7BI6nJSu1xN74TdiRXdRlI02ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3574fb775d84c2f64a19c1fd36a48cfcf863bf4a93a09a99259e4bb938235dbb","last_reissued_at":"2026-07-05T11:24:36.771214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:36.771214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16456","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":"2026-07-05T11:24:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1eixjx3lyBwOj5V9eH39BiKGQeELg1dwKF1Q/IiUijlE1OQFXQX9t8apSKXoUBfgZsGNWZ5GW5/kqMIxbF3nCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:50:08.896068Z"},"content_sha256":"0349119c43241faf3fde94113c1d992f4302831d692faae422858e9a1acbdc56","schema_version":"1.0","event_id":"sha256:0349119c43241faf3fde94113c1d992f4302831d692faae422858e9a1acbdc56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GV2PW525QTBPMSQZYH6TNJEM7T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Tensor-Train Parameterization for Efficient and Expressive Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao-Han Huck Yang, Chen-Yu Liu, Jun Qi, Min-Hsiu Hsieh, Sabato Marco Siniscalchi","submitted_at":"2025-06-19T16:46:23Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) is widely recognized for its parameter-efficient fine-tuning of large-scale neural models. However, standard LoRA independently optimizes low-rank matrices, which inherently limits its expressivity and generalization capabilities. While classical tensor-train (TT) decomposition can be separately employed on individual LoRA matrices, this work demonstrates that the classical TT-based approach neither significantly improves parameter efficiency nor achieves substantial performance gains. This paper proposes TensorGuide, a novel tensor-train-guided adaptation framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16456","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/2506.16456/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":"2026-07-05T11:24:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aJ3rDcgAjpjr3Y6ovKU+gO4n5BvFwmauTRF0cNgODJE5cBrUBjXueO/oT74+NIlTrhB+mnndUYwCJ9nvEMQFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:50:08.897151Z"},"content_sha256":"cee4f1764e76c1e93496eecea095eab738e8fc77ed4e2da751fae73fed70924e","schema_version":"1.0","event_id":"sha256:cee4f1764e76c1e93496eecea095eab738e8fc77ed4e2da751fae73fed70924e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GV2PW525QTBPMSQZYH6TNJEM7T/bundle.json","state_url":"https://pith.science/pith/GV2PW525QTBPMSQZYH6TNJEM7T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GV2PW525QTBPMSQZYH6TNJEM7T/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":"2026-08-13T12:50:08Z","links":{"resolver":"https://pith.science/pith/GV2PW525QTBPMSQZYH6TNJEM7T","bundle":"https://pith.science/pith/GV2PW525QTBPMSQZYH6TNJEM7T/bundle.json","state":"https://pith.science/pith/GV2PW525QTBPMSQZYH6TNJEM7T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GV2PW525QTBPMSQZYH6TNJEM7T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GV2PW525QTBPMSQZYH6TNJEM7T","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":"2a2c14f785c2e77c07b8b3b61753538d7853109ce052da7f79985a7aded0b836","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T16:46:23Z","title_canon_sha256":"61197f9241c0f7781e22ea27966bcc062f86bbab4ed6d2fbdc588e20c33086c5"},"schema_version":"1.0","source":{"id":"2506.16456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16456","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16456v1","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16456","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"GV2PW525QTBP","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_16","alias_value":"GV2PW525QTBPMSQZ","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_8","alias_value":"GV2PW525","created_at":"2026-07-05T11:24:36Z"}],"graph_snapshots":[{"event_id":"sha256:cee4f1764e76c1e93496eecea095eab738e8fc77ed4e2da751fae73fed70924e","target":"graph","created_at":"2026-07-05T11:24:36Z","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/2506.16456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-Rank Adaptation (LoRA) is widely recognized for its parameter-efficient fine-tuning of large-scale neural models. However, standard LoRA independently optimizes low-rank matrices, which inherently limits its expressivity and generalization capabilities. While classical tensor-train (TT) decomposition can be separately employed on individual LoRA matrices, this work demonstrates that the classical TT-based approach neither significantly improves parameter efficiency nor achieves substantial performance gains. This paper proposes TensorGuide, a novel tensor-train-guided adaptation framework ","authors_text":"Chao-Han Huck Yang, Chen-Yu Liu, Jun Qi, Min-Hsiu Hsieh, Sabato Marco Siniscalchi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T16:46:23Z","title":"Joint Tensor-Train Parameterization for Efficient and Expressive Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16456","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":"sha256:0349119c43241faf3fde94113c1d992f4302831d692faae422858e9a1acbdc56","target":"record","created_at":"2026-07-05T11:24:36Z","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":"2a2c14f785c2e77c07b8b3b61753538d7853109ce052da7f79985a7aded0b836","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T16:46:23Z","title_canon_sha256":"61197f9241c0f7781e22ea27966bcc062f86bbab4ed6d2fbdc588e20c33086c5"},"schema_version":"1.0","source":{"id":"2506.16456","kind":"arxiv","version":1}},"canonical_sha256":"3574fb775d84c2f64a19c1fd36a48cfcf863bf4a93a09a99259e4bb938235dbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3574fb775d84c2f64a19c1fd36a48cfcf863bf4a93a09a99259e4bb938235dbb","first_computed_at":"2026-07-05T11:24:36.771214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:36.771214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DuTBIcqs0c55tO5uRBM/fI9FW4PsjyKLPw51kI83L7yLYynuq+zXxwNrnrl7BI6nJSu1xN74TdiRXdRlI02ZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:36.771715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0349119c43241faf3fde94113c1d992f4302831d692faae422858e9a1acbdc56","sha256:cee4f1764e76c1e93496eecea095eab738e8fc77ed4e2da751fae73fed70924e"],"state_sha256":"4c6d110fd2b39a7c25f80371bbbf53ebc8880836c331eb7cda15959c1a66a0ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tl6No0+VQbLTPCwrYjG46vPpZvrrWTwYODfy6bQ9Zeg6tdJOE9NS+FcTtA9nOwF37hRZV4MORpIlHk+Iep8ZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T12:50:08.907839Z","bundle_sha256":"db6bfda1d138499f5a3e8b93f571e6e4a4fa52bc9cef7b213ce27458e6b6bc48"}}