{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KML447CBQF2HFLPDKQQAHQGE6Q","short_pith_number":"pith:KML447CB","canonical_record":{"source":{"id":"2605.31234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T12:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"085e777634862085edaf1a52f082feed1b0f5e51cfbc42e9dd6f173e98395933","abstract_canon_sha256":"467ddab62bb45071c3908222092d6b5f92e0aab779593561cd3e26d6c3fa3360"},"schema_version":"1.0"},"canonical_sha256":"5317ce7c41817472ade3542003c0c4f43178e90b6a5caab7224d0ac1555e7b38","source":{"kind":"arxiv","id":"2605.31234","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31234","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31234v1","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31234","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"KML447CBQF2H","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"KML447CBQF2HFLPD","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"KML447CB","created_at":"2026-06-01T01:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KML447CBQF2HFLPDKQQAHQGE6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2605.31234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T12:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"085e777634862085edaf1a52f082feed1b0f5e51cfbc42e9dd6f173e98395933","abstract_canon_sha256":"467ddab62bb45071c3908222092d6b5f92e0aab779593561cd3e26d6c3fa3360"},"schema_version":"1.0"},"canonical_sha256":"5317ce7c41817472ade3542003c0c4f43178e90b6a5caab7224d0ac1555e7b38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:05.534873Z","signature_b64":"yXCxImP10QaI5UF7Pu8+GAWBgB+fm5/7YPCg4SitBVQiPminunhLMyEpqPIUPIQZeeEf0znviHt/1HRpoFlACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5317ce7c41817472ade3542003c0c4f43178e90b6a5caab7224d0ac1555e7b38","last_reissued_at":"2026-06-01T01:04:05.534029Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:05.534029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.31234","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":"2026-06-01T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YarfrkpKjs/hFUq+wIb7JaK02J0Hnu+tom/R5TAYdY8nBM6ePJcGwLhiBUa7JYQvg6nx0UqyowsgOxORNe0nCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:18:49.150772Z"},"content_sha256":"1ab6062179786e21b8079ef7c962ff91ee15834241f74caf77e36297495c92e7","schema_version":"1.0","event_id":"sha256:1ab6062179786e21b8079ef7c962ff91ee15834241f74caf77e36297495c92e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KML447CBQF2HFLPDKQQAHQGE6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jianyu Chen, Puzhen Yuan, Xiang Zhu, Yichen Liu","submitted_at":"2026-05-29T12:36:30Z","abstract_excerpt":"Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies in both visual observations and executable actions. While latent action models reduce the action execution gap by learning action abstractions, they still rely on visual features. Thus, misaligned human and robot visual representations can lead to inconsistencies in policy inputs and induce domain-dependent latent actions, hindering effective co-training with human videos. To address this, we propose HARP, a human-robot aligned representati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31234","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/2605.31234/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":"2026-06-01T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0JWHCqCpsilIiS+Xi1K/XlwRZvGR1X85BcoMh6CUW3b/dfkWIM+E/lIqY8uHSWWeQTQWSqCYfA4bm3tAkbSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:18:49.151141Z"},"content_sha256":"e298dd087e85cd6c98fcf1aef71cd87f5c577cc0b9d6b6a9b86289cbf49a920b","schema_version":"1.0","event_id":"sha256:e298dd087e85cd6c98fcf1aef71cd87f5c577cc0b9d6b6a9b86289cbf49a920b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KML447CBQF2HFLPDKQQAHQGE6Q/bundle.json","state_url":"https://pith.science/pith/KML447CBQF2HFLPDKQQAHQGE6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KML447CBQF2HFLPDKQQAHQGE6Q/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":"2026-06-03T02:18:49Z","links":{"resolver":"https://pith.science/pith/KML447CBQF2HFLPDKQQAHQGE6Q","bundle":"https://pith.science/pith/KML447CBQF2HFLPDKQQAHQGE6Q/bundle.json","state":"https://pith.science/pith/KML447CBQF2HFLPDKQQAHQGE6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KML447CBQF2HFLPDKQQAHQGE6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KML447CBQF2HFLPDKQQAHQGE6Q","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":"467ddab62bb45071c3908222092d6b5f92e0aab779593561cd3e26d6c3fa3360","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T12:36:30Z","title_canon_sha256":"085e777634862085edaf1a52f082feed1b0f5e51cfbc42e9dd6f173e98395933"},"schema_version":"1.0","source":{"id":"2605.31234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31234","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31234v1","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31234","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"KML447CBQF2H","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"KML447CBQF2HFLPD","created_at":"2026-06-01T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"KML447CB","created_at":"2026-06-01T01:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:e298dd087e85cd6c98fcf1aef71cd87f5c577cc0b9d6b6a9b86289cbf49a920b","target":"graph","created_at":"2026-06-01T01:04:05Z","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/2605.31234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies in both visual observations and executable actions. While latent action models reduce the action execution gap by learning action abstractions, they still rely on visual features. Thus, misaligned human and robot visual representations can lead to inconsistencies in policy inputs and induce domain-dependent latent actions, hindering effective co-training with human videos. To address this, we propose HARP, a human-robot aligned representati","authors_text":"Jianyu Chen, Puzhen Yuan, Xiang Zhu, Yichen Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T12:36:30Z","title":"HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31234","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":"sha256:1ab6062179786e21b8079ef7c962ff91ee15834241f74caf77e36297495c92e7","target":"record","created_at":"2026-06-01T01:04:05Z","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":"467ddab62bb45071c3908222092d6b5f92e0aab779593561cd3e26d6c3fa3360","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T12:36:30Z","title_canon_sha256":"085e777634862085edaf1a52f082feed1b0f5e51cfbc42e9dd6f173e98395933"},"schema_version":"1.0","source":{"id":"2605.31234","kind":"arxiv","version":1}},"canonical_sha256":"5317ce7c41817472ade3542003c0c4f43178e90b6a5caab7224d0ac1555e7b38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5317ce7c41817472ade3542003c0c4f43178e90b6a5caab7224d0ac1555e7b38","first_computed_at":"2026-06-01T01:04:05.534029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:05.534029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yXCxImP10QaI5UF7Pu8+GAWBgB+fm5/7YPCg4SitBVQiPminunhLMyEpqPIUPIQZeeEf0znviHt/1HRpoFlACA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:05.534873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ab6062179786e21b8079ef7c962ff91ee15834241f74caf77e36297495c92e7","sha256:e298dd087e85cd6c98fcf1aef71cd87f5c577cc0b9d6b6a9b86289cbf49a920b"],"state_sha256":"698f91d5c239488d6a80797b465fa1c0f34a2d81adf84ee2903837b6a05309f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNTcqTiEWhspRxv/SZuiSz2c+XTm3c+Mu9/IoONE2J9ixn5Nbvt42brovAkCurftlf8B355k1Kl+48HVeI8HDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T02:18:49.153199Z","bundle_sha256":"5f971725dc44cfed9e53be53e9a5aba746644843f369266a406993d29734c601"}}