{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:U4Z5MCE3FU6XGJIXU7DBMHMSX4","short_pith_number":"pith:U4Z5MCE3","canonical_record":{"source":{"id":"2606.25700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T11:15:42Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3cc6b0cc9dc254ffd3e9f0806d64337a4942464380e02a3e8a4d52ba293c05ae","abstract_canon_sha256":"96205b4c1acdd73446e4be96da4253df154c7987c492187417105acaa0845dde"},"schema_version":"1.0"},"canonical_sha256":"a733d6089b2d3d732517a7c6161d92bf00f5902135718de90a2039a88c697def","source":{"kind":"arxiv","id":"2606.25700","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25700","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25700v1","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25700","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"U4Z5MCE3FU6X","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"U4Z5MCE3FU6XGJIX","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"U4Z5MCE3","created_at":"2026-06-25T01:18:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:U4Z5MCE3FU6XGJIXU7DBMHMSX4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.25700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T11:15:42Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3cc6b0cc9dc254ffd3e9f0806d64337a4942464380e02a3e8a4d52ba293c05ae","abstract_canon_sha256":"96205b4c1acdd73446e4be96da4253df154c7987c492187417105acaa0845dde"},"schema_version":"1.0"},"canonical_sha256":"a733d6089b2d3d732517a7c6161d92bf00f5902135718de90a2039a88c697def","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:13.121581Z","signature_b64":"KVsWL5uwtGyEP2euOJqvf88FjTDS860+WSfkIw3ZTvf4Ne5GKKm+W1IrA2ci0GE/Y3L/CX/TeJgq3Dd1VPXNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a733d6089b2d3d732517a7c6161d92bf00f5902135718de90a2039a88c697def","last_reissued_at":"2026-06-25T01:18:13.121171Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:13.121171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.25700","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":"2026-06-25T01:18:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aaAf+TogZwQAE58I8uXB2l5xCN5t/jEhvWyW/2/Vn1i1LpPRFOAjab/JfhMtLHLBOnEFMYZjW2lZ/AWa5tM1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:13:54.151089Z"},"content_sha256":"df28f52ae119c89f1bef6ef09470ad2db12161ffd797e30a07745bfc9908c9a9","schema_version":"1.0","event_id":"sha256:df28f52ae119c89f1bef6ef09470ad2db12161ffd797e30a07745bfc9908c9a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:U4Z5MCE3FU6XGJIXU7DBMHMSX4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Eirik M{\\o}ller Nilsen, Gard Sveipe, Jim Torresen, Kai Olav Ellefsen, Samuel Valland Lyngset, Tobias L{\\o}mo, Tor Viljen Raanaas","submitted_at":"2026-06-24T11:15:42Z","abstract_excerpt":"When fine-tuning Large Language Models (LLMs), there has been success in minimizing both memory usage and computation with Parameter-Efficient Fine-Tuning (PEFT), like Low Rank Adaptation (LoRA). In this article, we have explored whether this approach is transferable to the world of robotics and Reinforcement Learning (RL), allowing learning with reduced memory usage and improved computational performance. Specifically, we focused on a version of multi-task robotics, where a library of specialist policies are created. In such a library memory efficiency is especially important. We used a Proxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25700","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/2606.25700/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":"2026-06-25T01:18:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRcJt/D+kHBLPDi23V7ZTncP8ClLB1TZJRsu5/0F5Z4Q3CeRjgkGkJpyzR9n/DP58SADxSA03bQGKmsr45WvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:13:54.151491Z"},"content_sha256":"fc2e510706fcf7d58e8ca739f57975343e2f9d2a7bd64082eb6586097d8db6f0","schema_version":"1.0","event_id":"sha256:fc2e510706fcf7d58e8ca739f57975343e2f9d2a7bd64082eb6586097d8db6f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4Z5MCE3FU6XGJIXU7DBMHMSX4/bundle.json","state_url":"https://pith.science/pith/U4Z5MCE3FU6XGJIXU7DBMHMSX4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4Z5MCE3FU6XGJIXU7DBMHMSX4/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":"2026-07-06T16:13:54Z","links":{"resolver":"https://pith.science/pith/U4Z5MCE3FU6XGJIXU7DBMHMSX4","bundle":"https://pith.science/pith/U4Z5MCE3FU6XGJIXU7DBMHMSX4/bundle.json","state":"https://pith.science/pith/U4Z5MCE3FU6XGJIXU7DBMHMSX4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4Z5MCE3FU6XGJIXU7DBMHMSX4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U4Z5MCE3FU6XGJIXU7DBMHMSX4","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":"96205b4c1acdd73446e4be96da4253df154c7987c492187417105acaa0845dde","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T11:15:42Z","title_canon_sha256":"3cc6b0cc9dc254ffd3e9f0806d64337a4942464380e02a3e8a4d52ba293c05ae"},"schema_version":"1.0","source":{"id":"2606.25700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25700","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25700v1","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25700","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"U4Z5MCE3FU6X","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"U4Z5MCE3FU6XGJIX","created_at":"2026-06-25T01:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"U4Z5MCE3","created_at":"2026-06-25T01:18:13Z"}],"graph_snapshots":[{"event_id":"sha256:fc2e510706fcf7d58e8ca739f57975343e2f9d2a7bd64082eb6586097d8db6f0","target":"graph","created_at":"2026-06-25T01:18:13Z","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/2606.25700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When fine-tuning Large Language Models (LLMs), there has been success in minimizing both memory usage and computation with Parameter-Efficient Fine-Tuning (PEFT), like Low Rank Adaptation (LoRA). In this article, we have explored whether this approach is transferable to the world of robotics and Reinforcement Learning (RL), allowing learning with reduced memory usage and improved computational performance. Specifically, we focused on a version of multi-task robotics, where a library of specialist policies are created. In such a library memory efficiency is especially important. We used a Proxi","authors_text":"Eirik M{\\o}ller Nilsen, Gard Sveipe, Jim Torresen, Kai Olav Ellefsen, Samuel Valland Lyngset, Tobias L{\\o}mo, Tor Viljen Raanaas","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T11:15:42Z","title":"Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25700","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:df28f52ae119c89f1bef6ef09470ad2db12161ffd797e30a07745bfc9908c9a9","target":"record","created_at":"2026-06-25T01:18:13Z","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":"96205b4c1acdd73446e4be96da4253df154c7987c492187417105acaa0845dde","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T11:15:42Z","title_canon_sha256":"3cc6b0cc9dc254ffd3e9f0806d64337a4942464380e02a3e8a4d52ba293c05ae"},"schema_version":"1.0","source":{"id":"2606.25700","kind":"arxiv","version":1}},"canonical_sha256":"a733d6089b2d3d732517a7c6161d92bf00f5902135718de90a2039a88c697def","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a733d6089b2d3d732517a7c6161d92bf00f5902135718de90a2039a88c697def","first_computed_at":"2026-06-25T01:18:13.121171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:13.121171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KVsWL5uwtGyEP2euOJqvf88FjTDS860+WSfkIw3ZTvf4Ne5GKKm+W1IrA2ci0GE/Y3L/CX/TeJgq3Dd1VPXNDQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:13.121581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df28f52ae119c89f1bef6ef09470ad2db12161ffd797e30a07745bfc9908c9a9","sha256:fc2e510706fcf7d58e8ca739f57975343e2f9d2a7bd64082eb6586097d8db6f0"],"state_sha256":"0d5a8e29e9581b61f2555bcfd3ac7efd29b3f81be9ac773d7c1ce7e46aa57357"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LzaXmjOHiTig8tAy8TL6V6R0G5sH9fL/B+UjLfzLAMMN76vZAP4Ax4aAUXMksRkkn3eBO+1wWatkNuxq70Q/AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:13:54.153558Z","bundle_sha256":"0734c137547235d9ddbe7c46b19618b8a8a09fe5c0677ee386628cf483b29981"}}