{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PJ64HOC2ER7CND7FBSCAZBSH6P","short_pith_number":"pith:PJ64HOC2","canonical_record":{"source":{"id":"2606.14970","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-12T21:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"e0b7ca2723d762df38f575309f969365c01386f7d7c2bf39890b00c03e1d0989","abstract_canon_sha256":"3a0304ac0d5f3f4bdee048e774ae4504bbde55fa0d43d176dd19bcca8f72725e"},"schema_version":"1.0"},"canonical_sha256":"7a7dc3b85a247e268fe50c840c8647f3ca4417d459a9d6348e45c792f72d8c06","source":{"kind":"arxiv","id":"2606.14970","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.14970","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.14970v2","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14970","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"pith_short_12","alias_value":"PJ64HOC2ER7C","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"pith_short_16","alias_value":"PJ64HOC2ER7CND7F","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"pith_short_8","alias_value":"PJ64HOC2","created_at":"2026-06-23T03:13:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PJ64HOC2ER7CND7FBSCAZBSH6P","target":"record","payload":{"canonical_record":{"source":{"id":"2606.14970","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-12T21:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"e0b7ca2723d762df38f575309f969365c01386f7d7c2bf39890b00c03e1d0989","abstract_canon_sha256":"3a0304ac0d5f3f4bdee048e774ae4504bbde55fa0d43d176dd19bcca8f72725e"},"schema_version":"1.0"},"canonical_sha256":"7a7dc3b85a247e268fe50c840c8647f3ca4417d459a9d6348e45c792f72d8c06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:59.295353Z","signature_b64":"lXp2eocZeOfO+VzdCdAKpFOzf9zTJ6qGCkcDxqCCdFou7OEttaNDqag3PdIzzJprdaBqoGQM7CHgnaB5SnfbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a7dc3b85a247e268fe50c840c8647f3ca4417d459a9d6348e45c792f72d8c06","last_reissued_at":"2026-06-23T03:13:59.294865Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:59.294865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.14970","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eA95O6J4CPDxCHaPzhAGdEjz3iAoyxSDCbhBN9tjzh7qw1UE3K2Lda2jJf8cd+HR5m9GOldxJl9EW++iPE91CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:32:02.750931Z"},"content_sha256":"12f303dc11b2f3acf68ac3aedb2c8c035a131b05f7fec1933ca3d79e6ee90bce","schema_version":"1.0","event_id":"sha256:12f303dc11b2f3acf68ac3aedb2c8c035a131b05f7fec1933ca3d79e6ee90bce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PJ64HOC2ER7CND7FBSCAZBSH6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksandr Beznosikov, Daniil Medyakov, Dmitriy Bystrov, Dmitry Bylinkin","submitted_at":"2026-06-12T21:46:54Z","abstract_excerpt":"Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data. A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation, which requires storing activations, gradients, and optimizer states. Zeroth-order (ZO) optimization offers a memory-efficient alternative, but its performance is highly sensitive to the stepsize and smoothing parameter, often requiring costly task-specific tuning. Parameter-free (PF) optimization addresses this issue by ada"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14970","kind":"arxiv","version":2},"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/2606.14970/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":"2026-06-23T03:13:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AZDIt2IqGbfXT0wOrp1E74Ie2TGGZ6bszTZPUAE/hn0L03NeL3/0xhiBEh5zg3oOPg5pEuGsx75VUGmvP16vDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:32:02.751304Z"},"content_sha256":"8205cb867a705db3397fd9b83875e8ed183255ebf4a1a5c0262290df4d627421","schema_version":"1.0","event_id":"sha256:8205cb867a705db3397fd9b83875e8ed183255ebf4a1a5c0262290df4d627421"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/bundle.json","state_url":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/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":"2026-06-30T11:32:02Z","links":{"resolver":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P","bundle":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/bundle.json","state":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PJ64HOC2ER7CND7FBSCAZBSH6P","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":"3a0304ac0d5f3f4bdee048e774ae4504bbde55fa0d43d176dd19bcca8f72725e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-12T21:46:54Z","title_canon_sha256":"e0b7ca2723d762df38f575309f969365c01386f7d7c2bf39890b00c03e1d0989"},"schema_version":"1.0","source":{"id":"2606.14970","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.14970","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.14970v2","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14970","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"pith_short_12","alias_value":"PJ64HOC2ER7C","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"pith_short_16","alias_value":"PJ64HOC2ER7CND7F","created_at":"2026-06-23T03:13:59Z"},{"alias_kind":"pith_short_8","alias_value":"PJ64HOC2","created_at":"2026-06-23T03:13:59Z"}],"graph_snapshots":[{"event_id":"sha256:8205cb867a705db3397fd9b83875e8ed183255ebf4a1a5c0262290df4d627421","target":"graph","created_at":"2026-06-23T03:13:59Z","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/2606.14970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data. A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation, which requires storing activations, gradients, and optimizer states. Zeroth-order (ZO) optimization offers a memory-efficient alternative, but its performance is highly sensitive to the stepsize and smoothing parameter, often requiring costly task-specific tuning. Parameter-free (PF) optimization addresses this issue by ada","authors_text":"Aleksandr Beznosikov, Daniil Medyakov, Dmitriy Bystrov, Dmitry Bylinkin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-12T21:46:54Z","title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14970","kind":"arxiv","version":2},"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":"sha256:12f303dc11b2f3acf68ac3aedb2c8c035a131b05f7fec1933ca3d79e6ee90bce","target":"record","created_at":"2026-06-23T03:13:59Z","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":"3a0304ac0d5f3f4bdee048e774ae4504bbde55fa0d43d176dd19bcca8f72725e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-12T21:46:54Z","title_canon_sha256":"e0b7ca2723d762df38f575309f969365c01386f7d7c2bf39890b00c03e1d0989"},"schema_version":"1.0","source":{"id":"2606.14970","kind":"arxiv","version":2}},"canonical_sha256":"7a7dc3b85a247e268fe50c840c8647f3ca4417d459a9d6348e45c792f72d8c06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a7dc3b85a247e268fe50c840c8647f3ca4417d459a9d6348e45c792f72d8c06","first_computed_at":"2026-06-23T03:13:59.294865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:59.294865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lXp2eocZeOfO+VzdCdAKpFOzf9zTJ6qGCkcDxqCCdFou7OEttaNDqag3PdIzzJprdaBqoGQM7CHgnaB5SnfbAg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:59.295353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.14970","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12f303dc11b2f3acf68ac3aedb2c8c035a131b05f7fec1933ca3d79e6ee90bce","sha256:8205cb867a705db3397fd9b83875e8ed183255ebf4a1a5c0262290df4d627421"],"state_sha256":"cad7e0c8f3d53874d6be99d655466de9458b25f45d3afb4d348953830369bde0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pzma1Xf5jeybvHsncc71dVkMPlcMebeJ/Mro+VkfvB8j2h6CmOaEo62qwZ/a0b83Ta2EO9+qBbmIabAvrXM6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T11:32:02.753212Z","bundle_sha256":"5a9df30a73a8f793edba7537cea4bfc92cec3ff6542770d4eb9559dcf7156f1b"}}