{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4HJLBFPQO7QUB2SBI4BRKEUMPG","short_pith_number":"pith:4HJLBFPQ","canonical_record":{"source":{"id":"2401.11316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T20:25:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad07f869b8005b32a28d0fa52a12a3c4df855a97834bd867183a2e57e9732fc8","abstract_canon_sha256":"6361fedbeee42a2a1e547d09e5af6f4d061b5b8c7a25d5d692318c4b2a03caa7"},"schema_version":"1.0"},"canonical_sha256":"e1d2b095f077e140ea41470315128c79bceef647b05cad3aebdd6c0054398fff","source":{"kind":"arxiv","id":"2401.11316","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11316","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11316v1","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11316","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"pith_short_12","alias_value":"4HJLBFPQO7QU","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"pith_short_16","alias_value":"4HJLBFPQO7QUB2SB","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"pith_short_8","alias_value":"4HJLBFPQ","created_at":"2026-07-05T07:35:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4HJLBFPQO7QUB2SBI4BRKEUMPG","target":"record","payload":{"canonical_record":{"source":{"id":"2401.11316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T20:25:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad07f869b8005b32a28d0fa52a12a3c4df855a97834bd867183a2e57e9732fc8","abstract_canon_sha256":"6361fedbeee42a2a1e547d09e5af6f4d061b5b8c7a25d5d692318c4b2a03caa7"},"schema_version":"1.0"},"canonical_sha256":"e1d2b095f077e140ea41470315128c79bceef647b05cad3aebdd6c0054398fff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:48.796794Z","signature_b64":"KACoBKcPld9k0ArJ3H94OuoPitBcJiFGhZB18ij50d1CEmzByfpgR8WL9TRQFSyDoJGovvvlN6c2uE0zhLDpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d2b095f077e140ea41470315128c79bceef647b05cad3aebdd6c0054398fff","last_reissued_at":"2026-07-05T07:35:48.796383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:48.796383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.11316","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":"2026-07-05T07:35:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84fkGWVWxrqMhJAz8bAcQwwUT1q8ZCN0ije/iO4H0D8RU4ylUVYyWgLvYPilNqzpRLO/a4uo79Y2YIeLuNTLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:45:58.362020Z"},"content_sha256":"6b12bfc1affb7b9d6d7672755e601287439f92346cca002d1ccb557fb4a9ca6f","schema_version":"1.0","event_id":"sha256:6b12bfc1affb7b9d6d7672755e601287439f92346cca002d1ccb557fb4a9ca6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4HJLBFPQO7QUB2SBI4BRKEUMPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lior Wolf, Nadav Benedek","submitted_at":"2024-01-20T20:25:17Z","abstract_excerpt":"With the proliferation of large pre-trained language models (PLMs), fine-tuning all model parameters becomes increasingly inefficient, particularly when dealing with numerous downstream tasks that entail substantial training and storage costs. Several approaches aimed at achieving parameter-efficient fine-tuning (PEFT) have been proposed. Among them, Low-Rank Adaptation (LoRA) stands out as an archetypal method, incorporating trainable rank decomposition matrices into each target module. Nevertheless, LoRA does not consider the varying importance of each layer. To address these challenges, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11316","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/2401.11316/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":"2026-07-05T07:35:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/a39a2jcrRnDIoKqZ9e4YL77SUa/sL9SX0wvWP/z34eRuOy+IC1HnW7lzgZCC+24q5n1LoSAWRmhTPJwQ+HTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:45:58.362582Z"},"content_sha256":"2974215ef54201c57c274a68f3dab04ca95197aaa548af905f8e1f34f6026c07","schema_version":"1.0","event_id":"sha256:2974215ef54201c57c274a68f3dab04ca95197aaa548af905f8e1f34f6026c07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HJLBFPQO7QUB2SBI4BRKEUMPG/bundle.json","state_url":"https://pith.science/pith/4HJLBFPQO7QUB2SBI4BRKEUMPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HJLBFPQO7QUB2SBI4BRKEUMPG/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":"2026-08-12T22:45:58Z","links":{"resolver":"https://pith.science/pith/4HJLBFPQO7QUB2SBI4BRKEUMPG","bundle":"https://pith.science/pith/4HJLBFPQO7QUB2SBI4BRKEUMPG/bundle.json","state":"https://pith.science/pith/4HJLBFPQO7QUB2SBI4BRKEUMPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HJLBFPQO7QUB2SBI4BRKEUMPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4HJLBFPQO7QUB2SBI4BRKEUMPG","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":"6361fedbeee42a2a1e547d09e5af6f4d061b5b8c7a25d5d692318c4b2a03caa7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T20:25:17Z","title_canon_sha256":"ad07f869b8005b32a28d0fa52a12a3c4df855a97834bd867183a2e57e9732fc8"},"schema_version":"1.0","source":{"id":"2401.11316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11316","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11316v1","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11316","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"pith_short_12","alias_value":"4HJLBFPQO7QU","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"pith_short_16","alias_value":"4HJLBFPQO7QUB2SB","created_at":"2026-07-05T07:35:48Z"},{"alias_kind":"pith_short_8","alias_value":"4HJLBFPQ","created_at":"2026-07-05T07:35:48Z"}],"graph_snapshots":[{"event_id":"sha256:2974215ef54201c57c274a68f3dab04ca95197aaa548af905f8e1f34f6026c07","target":"graph","created_at":"2026-07-05T07:35:48Z","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/2401.11316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the proliferation of large pre-trained language models (PLMs), fine-tuning all model parameters becomes increasingly inefficient, particularly when dealing with numerous downstream tasks that entail substantial training and storage costs. Several approaches aimed at achieving parameter-efficient fine-tuning (PEFT) have been proposed. Among them, Low-Rank Adaptation (LoRA) stands out as an archetypal method, incorporating trainable rank decomposition matrices into each target module. Nevertheless, LoRA does not consider the varying importance of each layer. To address these challenges, we ","authors_text":"Lior Wolf, Nadav Benedek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T20:25:17Z","title":"PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11316","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":"sha256:6b12bfc1affb7b9d6d7672755e601287439f92346cca002d1ccb557fb4a9ca6f","target":"record","created_at":"2026-07-05T07:35:48Z","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":"6361fedbeee42a2a1e547d09e5af6f4d061b5b8c7a25d5d692318c4b2a03caa7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T20:25:17Z","title_canon_sha256":"ad07f869b8005b32a28d0fa52a12a3c4df855a97834bd867183a2e57e9732fc8"},"schema_version":"1.0","source":{"id":"2401.11316","kind":"arxiv","version":1}},"canonical_sha256":"e1d2b095f077e140ea41470315128c79bceef647b05cad3aebdd6c0054398fff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1d2b095f077e140ea41470315128c79bceef647b05cad3aebdd6c0054398fff","first_computed_at":"2026-07-05T07:35:48.796383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:48.796383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KACoBKcPld9k0ArJ3H94OuoPitBcJiFGhZB18ij50d1CEmzByfpgR8WL9TRQFSyDoJGovvvlN6c2uE0zhLDpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:48.796794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b12bfc1affb7b9d6d7672755e601287439f92346cca002d1ccb557fb4a9ca6f","sha256:2974215ef54201c57c274a68f3dab04ca95197aaa548af905f8e1f34f6026c07"],"state_sha256":"2c8349becf7c8bcb3d2948b1bdb56d42ccb0a13084068b36b6aaf4899bfe7e31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ynhi4vEk9RCk4C/Nz1Es4FKX/AF1eXD8wsa7fhpwgcYGFPoppMNvnFcG3bZf2GEQot6DFMZhKEMDic8Bp1leCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:45:58.366970Z","bundle_sha256":"b7ab23d6a1589dd7a193c7160fbe570b786c55f03c700389eda2a144cb4b78cb"}}