{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:O56Z7NAPGNCQCTHUE4Y64WKPDV","short_pith_number":"pith:O56Z7NAP","canonical_record":{"source":{"id":"2606.11854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T09:30:37Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"83ad85e456f8780c89f234c6b3368d899196dedc8b5e059c52ef9107e9cb4865","abstract_canon_sha256":"16522dfbd7e7abd0b90849b375bd7e38aa2ff22bcc827b1341b2ca9180afe97c"},"schema_version":"1.0"},"canonical_sha256":"777d9fb40f3345014cf42731ee594f1d6c3d4668474c6e7fc7c0c5195396e74e","source":{"kind":"arxiv","id":"2606.11854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11854","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11854v1","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11854","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"O56Z7NAPGNCQ","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"O56Z7NAPGNCQCTHU","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"O56Z7NAP","created_at":"2026-06-11T01:10:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:O56Z7NAPGNCQCTHUE4Y64WKPDV","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T09:30:37Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"83ad85e456f8780c89f234c6b3368d899196dedc8b5e059c52ef9107e9cb4865","abstract_canon_sha256":"16522dfbd7e7abd0b90849b375bd7e38aa2ff22bcc827b1341b2ca9180afe97c"},"schema_version":"1.0"},"canonical_sha256":"777d9fb40f3345014cf42731ee594f1d6c3d4668474c6e7fc7c0c5195396e74e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:11.885944Z","signature_b64":"thKzGN9uu5tfAs9KrGn1Tm5Tog8RB5YwG4bQl8+gY8qtQ9vnZ+m8aPvLKO8RiLFyZuzFSXSwOBMmIbP4pF2JCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"777d9fb40f3345014cf42731ee594f1d6c3d4668474c6e7fc7c0c5195396e74e","last_reissued_at":"2026-06-11T01:10:11.885437Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:11.885437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11854","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":"2026-06-11T01:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"99CpyIfrid53rJL5FvnpJl1ywtOlX+nb6ye4phntScgA9mw/A/p4qFnG0e1FKJw5fF5ZDmK8QzEVIQmAd9VwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:47:00.744801Z"},"content_sha256":"20ba4bb54fdb50cb847ccef3a174f4eb8db3b7675867c317e01f698e125bcc99","schema_version":"1.0","event_id":"sha256:20ba4bb54fdb50cb847ccef3a174f4eb8db3b7675867c317e01f698e125bcc99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:O56Z7NAPGNCQCTHUE4Y64WKPDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Michal Chudoba, Petra Galuscakova, Sergey Alyaev, Tomasz Wiktorski","submitted_at":"2026-06-10T09:30:37Z","abstract_excerpt":"There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LLM layers, Soft Prompting introduces additional fine-tuning-specific raw tokens to an LLM input. However, both require modification to the computational graphs of precompiled, preoptimized LLMs. As a result, neither is fully supported in high-throughput engines like vLLM. We propose fine-tuning with ART (Art-based Reinforcement Training). The method injects information into a frozen Multimodal Large Language Model (ML"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11854","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/2606.11854/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":"2026-06-11T01:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdcQJGemkbSotz1jjJXmfrT0xmklvlJ53LjCCOyAIAwJ/6pzn6qsUenBx5XK0rWuHt/eOWUw2WCGxQREbIz9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:47:00.745182Z"},"content_sha256":"78553d10d8d18e61bd2aea51f984ea00aabf48e5afb91232571d2335502d4037","schema_version":"1.0","event_id":"sha256:78553d10d8d18e61bd2aea51f984ea00aabf48e5afb91232571d2335502d4037"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O56Z7NAPGNCQCTHUE4Y64WKPDV/bundle.json","state_url":"https://pith.science/pith/O56Z7NAPGNCQCTHUE4Y64WKPDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O56Z7NAPGNCQCTHUE4Y64WKPDV/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":"2026-07-01T08:47:00Z","links":{"resolver":"https://pith.science/pith/O56Z7NAPGNCQCTHUE4Y64WKPDV","bundle":"https://pith.science/pith/O56Z7NAPGNCQCTHUE4Y64WKPDV/bundle.json","state":"https://pith.science/pith/O56Z7NAPGNCQCTHUE4Y64WKPDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O56Z7NAPGNCQCTHUE4Y64WKPDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O56Z7NAPGNCQCTHUE4Y64WKPDV","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":"16522dfbd7e7abd0b90849b375bd7e38aa2ff22bcc827b1341b2ca9180afe97c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T09:30:37Z","title_canon_sha256":"83ad85e456f8780c89f234c6b3368d899196dedc8b5e059c52ef9107e9cb4865"},"schema_version":"1.0","source":{"id":"2606.11854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11854","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11854v1","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11854","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"O56Z7NAPGNCQ","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"O56Z7NAPGNCQCTHU","created_at":"2026-06-11T01:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"O56Z7NAP","created_at":"2026-06-11T01:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:78553d10d8d18e61bd2aea51f984ea00aabf48e5afb91232571d2335502d4037","target":"graph","created_at":"2026-06-11T01:10:11Z","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/2606.11854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces additional weights between the LLM layers, Soft Prompting introduces additional fine-tuning-specific raw tokens to an LLM input. However, both require modification to the computational graphs of precompiled, preoptimized LLMs. As a result, neither is fully supported in high-throughput engines like vLLM. We propose fine-tuning with ART (Art-based Reinforcement Training). The method injects information into a frozen Multimodal Large Language Model (ML","authors_text":"Michal Chudoba, Petra Galuscakova, Sergey Alyaev, Tomasz Wiktorski","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T09:30:37Z","title":"Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11854","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":"sha256:20ba4bb54fdb50cb847ccef3a174f4eb8db3b7675867c317e01f698e125bcc99","target":"record","created_at":"2026-06-11T01:10:11Z","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":"16522dfbd7e7abd0b90849b375bd7e38aa2ff22bcc827b1341b2ca9180afe97c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T09:30:37Z","title_canon_sha256":"83ad85e456f8780c89f234c6b3368d899196dedc8b5e059c52ef9107e9cb4865"},"schema_version":"1.0","source":{"id":"2606.11854","kind":"arxiv","version":1}},"canonical_sha256":"777d9fb40f3345014cf42731ee594f1d6c3d4668474c6e7fc7c0c5195396e74e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"777d9fb40f3345014cf42731ee594f1d6c3d4668474c6e7fc7c0c5195396e74e","first_computed_at":"2026-06-11T01:10:11.885437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:11.885437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"thKzGN9uu5tfAs9KrGn1Tm5Tog8RB5YwG4bQl8+gY8qtQ9vnZ+m8aPvLKO8RiLFyZuzFSXSwOBMmIbP4pF2JCQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:11.885944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20ba4bb54fdb50cb847ccef3a174f4eb8db3b7675867c317e01f698e125bcc99","sha256:78553d10d8d18e61bd2aea51f984ea00aabf48e5afb91232571d2335502d4037"],"state_sha256":"3102ce70a391babfa82e4e43cc6e82f8858b53181d83586233b41eb4a58f998e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wHKV2IhofX70svU0fQ3VYqSJxHyq4mp1dNDIx/xcc50L4iQenF1O7x0CJsvwBdclyyo/osCyiXXigV73acV8Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T08:47:00.747266Z","bundle_sha256":"328bd8afdb3d6d2c89eb4aff05c11fc01b4b702f3cba5a93967c4391da461ceb"}}