{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JMIT4CPBVRXJ4CMG4TU5KB7TXP","short_pith_number":"pith:JMIT4CPB","schema_version":"1.0","canonical_sha256":"4b113e09e1ac6e9e0986e4e9d507f3bbe47b113c5d9a26a15d885b7186bb2479","source":{"kind":"arxiv","id":"2606.29028","version":1},"attestation_state":"computed","paper":{"title":"Keypose Exploration: Efficient Automatic Trajectory Labelling and Cross-Embodiment Policy Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hang Xu, Jia Pan, Yizhou Chen, Yupu Lu","submitted_at":"2026-06-27T17:48:39Z","abstract_excerpt":"Keypose-based manipulation decomposes tasks into critical waypoints to simplify policy learning for long-horizon tasks, but existing approaches rely on task-specific heuristics or manual annotation to extract keyposes from demonstrations. We present an automatic trajectory labelling pipeline for grasp-related tasks. This pipeline combines vision-language models (VLMs) for semantic event detection with classical trajectory analysis for precise temporal alignment, requiring VLM inference only on one single demo among repeating ones per task. Using the labelled data, we train a keypose-guided Dif"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.29028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-27T17:48:39Z","cross_cats_sorted":[],"title_canon_sha256":"f45f6010ff51c1b3de771564b1b27f53f9e2fe873ea04add4ba374eee394f2a3","abstract_canon_sha256":"e259aea3dcee0cfb98d79d61b2f3b5d8b54ebb38072a792e956e014c8af15c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:49.924845Z","signature_b64":"v0VK+ngpGv7mmDTCN0jFDY61qmcAO2PzwhtN3BpTHOiQ85k2g5odokQwdDwp+qb8VQBlROOLcdeSoJGO3PH8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b113e09e1ac6e9e0986e4e9d507f3bbe47b113c5d9a26a15d885b7186bb2479","last_reissued_at":"2026-06-30T01:17:49.924376Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:49.924376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keypose Exploration: Efficient Automatic Trajectory Labelling and Cross-Embodiment Policy Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hang Xu, Jia Pan, Yizhou Chen, Yupu Lu","submitted_at":"2026-06-27T17:48:39Z","abstract_excerpt":"Keypose-based manipulation decomposes tasks into critical waypoints to simplify policy learning for long-horizon tasks, but existing approaches rely on task-specific heuristics or manual annotation to extract keyposes from demonstrations. We present an automatic trajectory labelling pipeline for grasp-related tasks. This pipeline combines vision-language models (VLMs) for semantic event detection with classical trajectory analysis for precise temporal alignment, requiring VLM inference only on one single demo among repeating ones per task. Using the labelled data, we train a keypose-guided Dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29028","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/2606.29028/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.29028","created_at":"2026-06-30T01:17:49.924441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29028v1","created_at":"2026-06-30T01:17:49.924441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29028","created_at":"2026-06-30T01:17:49.924441+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMIT4CPBVRXJ","created_at":"2026-06-30T01:17:49.924441+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMIT4CPBVRXJ4CMG","created_at":"2026-06-30T01:17:49.924441+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMIT4CPB","created_at":"2026-06-30T01:17:49.924441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP","json":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP.json","graph_json":"https://pith.science/api/pith-number/JMIT4CPBVRXJ4CMG4TU5KB7TXP/graph.json","events_json":"https://pith.science/api/pith-number/JMIT4CPBVRXJ4CMG4TU5KB7TXP/events.json","paper":"https://pith.science/paper/JMIT4CPB"},"agent_actions":{"view_html":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP","download_json":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP.json","view_paper":"https://pith.science/paper/JMIT4CPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29028&json=true","fetch_graph":"https://pith.science/api/pith-number/JMIT4CPBVRXJ4CMG4TU5KB7TXP/graph.json","fetch_events":"https://pith.science/api/pith-number/JMIT4CPBVRXJ4CMG4TU5KB7TXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP/action/storage_attestation","attest_author":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP/action/author_attestation","sign_citation":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP/action/citation_signature","submit_replication":"https://pith.science/pith/JMIT4CPBVRXJ4CMG4TU5KB7TXP/action/replication_record"}},"created_at":"2026-06-30T01:17:49.924441+00:00","updated_at":"2026-06-30T01:17:49.924441+00:00"}