{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OF4OS3ETOCJGCCEAZ4TWFAVCKY","short_pith_number":"pith:OF4OS3ET","canonical_record":{"source":{"id":"2505.19080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T10:24:44Z","cross_cats_sorted":[],"title_canon_sha256":"2a2a12c05f0ae10501afeb53a319bfa6c10736bea2a437adbc98271b57760de5","abstract_canon_sha256":"8b049ad687759dfb82a49da76b5acb23875d05beede317d40b87550995f7d388"},"schema_version":"1.0"},"canonical_sha256":"7178e96c937092610880cf276282a25601ad123a9c31e3a1d1a6f910976221fe","source":{"kind":"arxiv","id":"2505.19080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19080","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19080v1","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19080","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"OF4OS3ETOCJG","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"OF4OS3ETOCJGCCEA","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"OF4OS3ET","created_at":"2026-07-05T11:09:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OF4OS3ETOCJGCCEAZ4TWFAVCKY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T10:24:44Z","cross_cats_sorted":[],"title_canon_sha256":"2a2a12c05f0ae10501afeb53a319bfa6c10736bea2a437adbc98271b57760de5","abstract_canon_sha256":"8b049ad687759dfb82a49da76b5acb23875d05beede317d40b87550995f7d388"},"schema_version":"1.0"},"canonical_sha256":"7178e96c937092610880cf276282a25601ad123a9c31e3a1d1a6f910976221fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:24.567118Z","signature_b64":"KqVq1xXwWepR1AIckkNVxO7yWGxMeujKUtK89FZ0/c7FQpdnMwfE8/Di0jNjXnh58WPF5NteeKwuvg30CmWuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7178e96c937092610880cf276282a25601ad123a9c31e3a1d1a6f910976221fe","last_reissued_at":"2026-07-05T11:09:24.566619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:24.566619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19080","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":"2026-07-05T11:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZdgPPrAQ5Dwe0CIrzUq7aSbrliMGJD27D+ag/XH+ko9fcHc9uAhStgdXhBGklDlxvmdUB4J1QFo8BATD7xtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:38:02.824727Z"},"content_sha256":"571a8a891f556e403d20a67086db3bc033b27e50a01d516fa7769d6a726829ae","schema_version":"1.0","event_id":"sha256:571a8a891f556e403d20a67086db3bc033b27e50a01d516fa7769d6a726829ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OF4OS3ETOCJGCCEAZ4TWFAVCKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Duy Ho Minh Nguyen, Khang Minh Nguyen, Minh Nhat Vu, Tan Quang Nguyen, Tuan Van Vo","submitted_at":"2025-05-25T10:24:44Z","abstract_excerpt":"Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into robotic actions. Despite their recent advancements, VLAs often overlook the explicit reasoning and only learn the functional input-action mappings, omitting these crucial logical steps for interpretability and generalization for complex, long-horizon manipulation tasks. In this work, we propose \\textit{ReFineVLA}, a multimodal reasoning-aware framework that fine-tunes VLAs with teacher-guided reasons. We fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19080","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/2505.19080/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":"2026-07-05T11:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yDPcTdb0/k90l1cwUg47CtbQkzF1KdXbT4X4Dkf0cJXLQALroauu3/tgrWX2pJEEWHeDeKPKqswVbkCeecSEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:38:02.825223Z"},"content_sha256":"05d3b9f63df262a6612c3cc754703f11c652ce6fab899fbe33b82bc92a579e2d","schema_version":"1.0","event_id":"sha256:05d3b9f63df262a6612c3cc754703f11c652ce6fab899fbe33b82bc92a579e2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OF4OS3ETOCJGCCEAZ4TWFAVCKY/bundle.json","state_url":"https://pith.science/pith/OF4OS3ETOCJGCCEAZ4TWFAVCKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OF4OS3ETOCJGCCEAZ4TWFAVCKY/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":"2026-08-08T00:38:02Z","links":{"resolver":"https://pith.science/pith/OF4OS3ETOCJGCCEAZ4TWFAVCKY","bundle":"https://pith.science/pith/OF4OS3ETOCJGCCEAZ4TWFAVCKY/bundle.json","state":"https://pith.science/pith/OF4OS3ETOCJGCCEAZ4TWFAVCKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OF4OS3ETOCJGCCEAZ4TWFAVCKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OF4OS3ETOCJGCCEAZ4TWFAVCKY","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":"8b049ad687759dfb82a49da76b5acb23875d05beede317d40b87550995f7d388","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T10:24:44Z","title_canon_sha256":"2a2a12c05f0ae10501afeb53a319bfa6c10736bea2a437adbc98271b57760de5"},"schema_version":"1.0","source":{"id":"2505.19080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19080","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19080v1","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19080","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"OF4OS3ETOCJG","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"OF4OS3ETOCJGCCEA","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"OF4OS3ET","created_at":"2026-07-05T11:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:05d3b9f63df262a6612c3cc754703f11c652ce6fab899fbe33b82bc92a579e2d","target":"graph","created_at":"2026-07-05T11:09:24Z","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/2505.19080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into robotic actions. Despite their recent advancements, VLAs often overlook the explicit reasoning and only learn the functional input-action mappings, omitting these crucial logical steps for interpretability and generalization for complex, long-horizon manipulation tasks. In this work, we propose \\textit{ReFineVLA}, a multimodal reasoning-aware framework that fine-tunes VLAs with teacher-guided reasons. We fir","authors_text":"Duy Ho Minh Nguyen, Khang Minh Nguyen, Minh Nhat Vu, Tan Quang Nguyen, Tuan Van Vo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T10:24:44Z","title":"ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19080","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":"sha256:571a8a891f556e403d20a67086db3bc033b27e50a01d516fa7769d6a726829ae","target":"record","created_at":"2026-07-05T11:09:24Z","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":"8b049ad687759dfb82a49da76b5acb23875d05beede317d40b87550995f7d388","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T10:24:44Z","title_canon_sha256":"2a2a12c05f0ae10501afeb53a319bfa6c10736bea2a437adbc98271b57760de5"},"schema_version":"1.0","source":{"id":"2505.19080","kind":"arxiv","version":1}},"canonical_sha256":"7178e96c937092610880cf276282a25601ad123a9c31e3a1d1a6f910976221fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7178e96c937092610880cf276282a25601ad123a9c31e3a1d1a6f910976221fe","first_computed_at":"2026-07-05T11:09:24.566619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:24.566619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KqVq1xXwWepR1AIckkNVxO7yWGxMeujKUtK89FZ0/c7FQpdnMwfE8/Di0jNjXnh58WPF5NteeKwuvg30CmWuBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:24.567118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:571a8a891f556e403d20a67086db3bc033b27e50a01d516fa7769d6a726829ae","sha256:05d3b9f63df262a6612c3cc754703f11c652ce6fab899fbe33b82bc92a579e2d"],"state_sha256":"ca4991784e36ffb2735556dd97dc7ab3fa438e8f2f4bfbc9619076f4953633a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/CNglv9yyA4yNhIqATfjpRtJurIqXIc7bELGuCDmuRC9r1ssjZRMjJzEUQsahwq4UeDhKeBTe9Ka9ADgOjJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:38:02.828997Z","bundle_sha256":"fd318ba6d27d75ab806dbf31e9e569696fc1b8e60edd4706ace4cca44965b648"}}