{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N33R4Q4AI2S6PXRKBGGX2EAZTP","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":"69989ca2e2b8cfff7766b1f33b23bf0484bf73a484a3616b31053989d7446e23","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-17T21:31:23Z","title_canon_sha256":"adc35f59dc7e1ab296411b366a4d68067fc19f637ce3e1e7fa16b5ab4055c727"},"schema_version":"1.0","source":{"id":"2504.13351","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13351","created_at":"2026-07-05T10:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13351v1","created_at":"2026-07-05T10:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13351","created_at":"2026-07-05T10:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"N33R4Q4AI2S6","created_at":"2026-07-05T10:50:53Z"},{"alias_kind":"pith_short_16","alias_value":"N33R4Q4AI2S6PXRK","created_at":"2026-07-05T10:50:53Z"},{"alias_kind":"pith_short_8","alias_value":"N33R4Q4A","created_at":"2026-07-05T10:50:53Z"}],"graph_snapshots":[{"event_id":"sha256:362f10876d7e917e975157a48c6f413115e656ccd674d6bef737b29e581b9db6","target":"graph","created_at":"2026-07-05T10:50:53Z","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/2504.13351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to perform manipulation tasks from human videos is a promising approach for teaching robots. However, many manipulation tasks require changing control parameters during task execution, such as force, which visual data alone cannot capture. In this work, we leverage sensing devices such as armbands that measure human muscle activities and microphones that record sound, to capture the details in the human manipulation process, and enable robots to extract task plans and control parameters to perform the same task. To achieve this, we introduce Chain-of-Modality (CoM), a prompting strate","authors_text":"Chen Wang, C. Karen Liu, Fei Xia, Jacky Liang, Jie Tan, Li Fei-Fei, Ruohan Zhang, Tingnan Zhang, Wenhao Yu","cross_cats":["cs.AI","cs.HC","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-17T21:31:23Z","title":"Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13351","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":"sha256:86cb2865010bd9a0b47583d6494b50a5a3f18ac52f9df3498bfd1927edf967f9","target":"record","created_at":"2026-07-05T10:50:53Z","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":"69989ca2e2b8cfff7766b1f33b23bf0484bf73a484a3616b31053989d7446e23","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-17T21:31:23Z","title_canon_sha256":"adc35f59dc7e1ab296411b366a4d68067fc19f637ce3e1e7fa16b5ab4055c727"},"schema_version":"1.0","source":{"id":"2504.13351","kind":"arxiv","version":1}},"canonical_sha256":"6ef71e438046a5e7de2a098d7d10199bd6573b0ac83ba4842bde9fc5cb3dce07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ef71e438046a5e7de2a098d7d10199bd6573b0ac83ba4842bde9fc5cb3dce07","first_computed_at":"2026-07-05T10:50:53.522253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:53.522253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ki7NZaKoiHsxc5bXMuzs0wYFhg7gxcnSRYhFZBplzztUVuRnJXOsYx/7sWSPeuQEFCJ3ffRMQy2nbxkqOcLyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:53.522703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13351","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86cb2865010bd9a0b47583d6494b50a5a3f18ac52f9df3498bfd1927edf967f9","sha256:362f10876d7e917e975157a48c6f413115e656ccd674d6bef737b29e581b9db6"],"state_sha256":"068aa0cae38280cd8dcf06d4500d31724aaa8fe1befca99a7e3cadcb22746fe0"}