{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5473GQFIAYTVLSJ6GGWFFNMPBI","short_pith_number":"pith:5473GQFI","schema_version":"1.0","canonical_sha256":"ef3fb340a8062755c93e31ac52b58f0a35220ba316ade657a4c414cf5e26b265","source":{"kind":"arxiv","id":"2409.07914","version":3},"attestation_state":"computed","paper":{"title":"InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Andrew Lee, Ian Chuang, Iman Soltani, Ling-Yuan Chen","submitted_at":"2024-09-12T10:30:44Z","abstract_excerpt":"Bimanual manipulation presents unique challenges compared to unimanual tasks due to the complexity of coordinating two robotic arms. In this paper, we introduce InterACT: Inter-dependency aware Action Chunking with Hierarchical Attention Transformers, a novel imitation learning framework designed specifically for bimanual manipulation. InterACT leverages hierarchical attention mechanisms to effectively capture inter-dependencies between dual-arm joint states and visual inputs. The framework comprises a Hierarchical Attention Encoder, which processes multi-modal inputs through segment-wise and "},"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":"2409.07914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-12T10:30:44Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"cfec147295fc524f48ca125677a16c2c8e5960fcf33f517cb08c412de9f83f8e","abstract_canon_sha256":"d896f10ec99860fe244ccd7c9e9801984ac68366e8473db057811f1aefb2bc7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:07.447696Z","signature_b64":"tQiHvhYbQ7kL01/568lPhRGrUfCD6XMR2s9kuwSJ3CYe+Umcu4ZkYkDZnQbRduFLNe99an1W/N62ZPaZuy4BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3fb340a8062755c93e31ac52b58f0a35220ba316ade657a4c414cf5e26b265","last_reissued_at":"2026-07-05T09:21:07.447182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:07.447182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Andrew Lee, Ian Chuang, Iman Soltani, Ling-Yuan Chen","submitted_at":"2024-09-12T10:30:44Z","abstract_excerpt":"Bimanual manipulation presents unique challenges compared to unimanual tasks due to the complexity of coordinating two robotic arms. In this paper, we introduce InterACT: Inter-dependency aware Action Chunking with Hierarchical Attention Transformers, a novel imitation learning framework designed specifically for bimanual manipulation. InterACT leverages hierarchical attention mechanisms to effectively capture inter-dependencies between dual-arm joint states and visual inputs. The framework comprises a Hierarchical Attention Encoder, which processes multi-modal inputs through segment-wise and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07914","kind":"arxiv","version":3},"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/2409.07914/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":"2409.07914","created_at":"2026-07-05T09:21:07.447243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07914v3","created_at":"2026-07-05T09:21:07.447243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07914","created_at":"2026-07-05T09:21:07.447243+00:00"},{"alias_kind":"pith_short_12","alias_value":"5473GQFIAYTV","created_at":"2026-07-05T09:21:07.447243+00:00"},{"alias_kind":"pith_short_16","alias_value":"5473GQFIAYTVLSJ6","created_at":"2026-07-05T09:21:07.447243+00:00"},{"alias_kind":"pith_short_8","alias_value":"5473GQFI","created_at":"2026-07-05T09:21:07.447243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11114","citing_title":"SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI","json":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI.json","graph_json":"https://pith.science/api/pith-number/5473GQFIAYTVLSJ6GGWFFNMPBI/graph.json","events_json":"https://pith.science/api/pith-number/5473GQFIAYTVLSJ6GGWFFNMPBI/events.json","paper":"https://pith.science/paper/5473GQFI"},"agent_actions":{"view_html":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI","download_json":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI.json","view_paper":"https://pith.science/paper/5473GQFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07914&json=true","fetch_graph":"https://pith.science/api/pith-number/5473GQFIAYTVLSJ6GGWFFNMPBI/graph.json","fetch_events":"https://pith.science/api/pith-number/5473GQFIAYTVLSJ6GGWFFNMPBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI/action/storage_attestation","attest_author":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI/action/author_attestation","sign_citation":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI/action/citation_signature","submit_replication":"https://pith.science/pith/5473GQFIAYTVLSJ6GGWFFNMPBI/action/replication_record"}},"created_at":"2026-07-05T09:21:07.447243+00:00","updated_at":"2026-07-05T09:21:07.447243+00:00"}