{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6CFE6QDMDTLNO4P4ZUZZWSXWPU","short_pith_number":"pith:6CFE6QDM","canonical_record":{"source":{"id":"2605.29577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:22:49Z","cross_cats_sorted":[],"title_canon_sha256":"c62bc3658aa49eb73ee708a968a8f7dc03276404aaf62cfb28e241e4d1fc5af1","abstract_canon_sha256":"4d6a90cd0cf6b3aeac222582e7e6115cb01d7ac71a0fb3387f82a17ab1788e68"},"schema_version":"1.0"},"canonical_sha256":"f08a4f406c1cd6d771fccd339b4af67d3bef0096483d587a183b223ea24076d2","source":{"kind":"arxiv","id":"2605.29577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29577","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29577v1","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29577","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"6CFE6QDMDTLN","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"6CFE6QDMDTLNO4P4","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"6CFE6QDM","created_at":"2026-05-29T01:05:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6CFE6QDMDTLNO4P4ZUZZWSXWPU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:22:49Z","cross_cats_sorted":[],"title_canon_sha256":"c62bc3658aa49eb73ee708a968a8f7dc03276404aaf62cfb28e241e4d1fc5af1","abstract_canon_sha256":"4d6a90cd0cf6b3aeac222582e7e6115cb01d7ac71a0fb3387f82a17ab1788e68"},"schema_version":"1.0"},"canonical_sha256":"f08a4f406c1cd6d771fccd339b4af67d3bef0096483d587a183b223ea24076d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:48.492225Z","signature_b64":"2XSu43juw/7m98GgnDQRTtQeQhliK/Zm1E4/54dldYN7Ny2PMDsgchkd9BOR3oarlHN8nwKqcfw4hWZdygw5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08a4f406c1cd6d771fccd339b4af67d3bef0096483d587a183b223ea24076d2","last_reissued_at":"2026-05-29T01:05:48.491454Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:48.491454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29577","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":"2026-05-29T01:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17BLrrbcOhuCtFZjREyOjWK5tAJX9xppN18ky045YwdEaqsgjHWLwpBN40aXIbly8olFozWz4athKrlZmzyMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:47:30.052389Z"},"content_sha256":"f6259656848aa19ed759bc861774a84c4d869b4a5ebb97f65b511614c6111788","schema_version":"1.0","event_id":"sha256:f6259656848aa19ed759bc861774a84c4d869b4a5ebb97f65b511614c6111788"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6CFE6QDMDTLNO4P4ZUZZWSXWPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyunwoo J. Kim, Injae Kim, Jihwan Park, Kyujin Lee, Minseok Joo, Yejun Ju","submitted_at":"2026-05-28T08:22:49Z","abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising framework that unifies perception, reasoning, and control for robot manipulation by adapting pretrained vision-language models (VLMs) to action prediction. However, VLM-derived representations are often insensitive to subtle visual distinctions required for low-level control, causing state aliasing between visually similar states that require substantially different actions. Prior VLA studies improve visual understanding by generating visual or reasoning outputs, such as future frames, 2D grounding points or traces, or intermediat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29577","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/2605.29577/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":"2026-05-29T01:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fbuxFiyFJYliHdAKb89oYoISlSCFJL4VM36TtrkPT/f5+5Az9qGVttZ029XOUdq3CAl5AR67hLu2hCXR4wzfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:47:30.053111Z"},"content_sha256":"4316c9aabf53938697f6ccb4efca9e47c3b08b34e746392fbf081ff4a9de9aad","schema_version":"1.0","event_id":"sha256:4316c9aabf53938697f6ccb4efca9e47c3b08b34e746392fbf081ff4a9de9aad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CFE6QDMDTLNO4P4ZUZZWSXWPU/bundle.json","state_url":"https://pith.science/pith/6CFE6QDMDTLNO4P4ZUZZWSXWPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CFE6QDMDTLNO4P4ZUZZWSXWPU/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":"2026-05-30T07:47:30Z","links":{"resolver":"https://pith.science/pith/6CFE6QDMDTLNO4P4ZUZZWSXWPU","bundle":"https://pith.science/pith/6CFE6QDMDTLNO4P4ZUZZWSXWPU/bundle.json","state":"https://pith.science/pith/6CFE6QDMDTLNO4P4ZUZZWSXWPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CFE6QDMDTLNO4P4ZUZZWSXWPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6CFE6QDMDTLNO4P4ZUZZWSXWPU","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":"4d6a90cd0cf6b3aeac222582e7e6115cb01d7ac71a0fb3387f82a17ab1788e68","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:22:49Z","title_canon_sha256":"c62bc3658aa49eb73ee708a968a8f7dc03276404aaf62cfb28e241e4d1fc5af1"},"schema_version":"1.0","source":{"id":"2605.29577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29577","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29577v1","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29577","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"6CFE6QDMDTLN","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"6CFE6QDMDTLNO4P4","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"6CFE6QDM","created_at":"2026-05-29T01:05:48Z"}],"graph_snapshots":[{"event_id":"sha256:4316c9aabf53938697f6ccb4efca9e47c3b08b34e746392fbf081ff4a9de9aad","target":"graph","created_at":"2026-05-29T01:05:48Z","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/2605.29577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising framework that unifies perception, reasoning, and control for robot manipulation by adapting pretrained vision-language models (VLMs) to action prediction. However, VLM-derived representations are often insensitive to subtle visual distinctions required for low-level control, causing state aliasing between visually similar states that require substantially different actions. Prior VLA studies improve visual understanding by generating visual or reasoning outputs, such as future frames, 2D grounding points or traces, or intermediat","authors_text":"Hyunwoo J. Kim, Injae Kim, Jihwan Park, Kyujin Lee, Minseok Joo, Yejun Ju","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:22:49Z","title":"Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29577","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:f6259656848aa19ed759bc861774a84c4d869b4a5ebb97f65b511614c6111788","target":"record","created_at":"2026-05-29T01:05:48Z","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":"4d6a90cd0cf6b3aeac222582e7e6115cb01d7ac71a0fb3387f82a17ab1788e68","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:22:49Z","title_canon_sha256":"c62bc3658aa49eb73ee708a968a8f7dc03276404aaf62cfb28e241e4d1fc5af1"},"schema_version":"1.0","source":{"id":"2605.29577","kind":"arxiv","version":1}},"canonical_sha256":"f08a4f406c1cd6d771fccd339b4af67d3bef0096483d587a183b223ea24076d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f08a4f406c1cd6d771fccd339b4af67d3bef0096483d587a183b223ea24076d2","first_computed_at":"2026-05-29T01:05:48.491454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:48.491454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2XSu43juw/7m98GgnDQRTtQeQhliK/Zm1E4/54dldYN7Ny2PMDsgchkd9BOR3oarlHN8nwKqcfw4hWZdygw5Ag==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:48.492225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6259656848aa19ed759bc861774a84c4d869b4a5ebb97f65b511614c6111788","sha256:4316c9aabf53938697f6ccb4efca9e47c3b08b34e746392fbf081ff4a9de9aad"],"state_sha256":"fb7c6b2ed7d7234f9b2d5b17b7d3cb0ed82d63e3e24ee4dde088d71cd3bbc565"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5saa5fO7gmFDCbYW1tVtdSUNqVaisGYyGsLJwZpGLjTxMU4D0LMQOoERilz5Ko3bfm57TexS6N3e3HJNfJe8BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:47:30.056613Z","bundle_sha256":"c47c6bc1f8704c915683fd2856ba1b0fb2ac886761170309157e9cb0619430a1"}}