{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I73LUCKFHIM7PHWFI5PCYMTLFO","short_pith_number":"pith:I73LUCKF","schema_version":"1.0","canonical_sha256":"47f6ba09453a19f79ec5475e2c326b2ba62f167b99d477a892d9db5a448a6c50","source":{"kind":"arxiv","id":"2504.12284","version":1},"attestation_state":"computed","paper":{"title":"How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Prakash, Benjamin Lundell, David Forsyth, Dmitry Andreychuk, Harpreet Sawhney, Saurabh Gupta","submitted_at":"2025-04-16T17:48:12Z","abstract_excerpt":"We tackle the novel problem of predicting 3D hand motion and contact maps (or Interaction Trajectories) given a single RGB view, action text, and a 3D contact point on the object as input. Our approach consists of (1) Interaction Codebook: a VQVAE model to learn a latent codebook of hand poses and contact points, effectively tokenizing interaction trajectories, (2) Interaction Predictor: a transformer-decoder module to predict the interaction trajectory from test time inputs by using an indexer module to retrieve a latent affordance from the learned codebook. To train our model, we develop a d"},"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":"2504.12284","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T17:48:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4981690287d86b1bb60a4437396b3a67e14952e8c801a0d762c6996cca20f39c","abstract_canon_sha256":"dfbdc52f99d2acd2bc6d22d3a66f345eb88c2dc8ed95f0ef71d8a16f9a1d7347"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:05.869953Z","signature_b64":"pro1SQWnQl0fqzC9QIThVJe/K7G0RkRDkAIubmL+ylBYQlslbBmuKaXdTFNsLrt8Bf4gXtVM9pfEWNYIzzXDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f6ba09453a19f79ec5475e2c326b2ba62f167b99d477a892d9db5a448a6c50","last_reissued_at":"2026-07-05T10:50:05.869394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:05.869394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Prakash, Benjamin Lundell, David Forsyth, Dmitry Andreychuk, Harpreet Sawhney, Saurabh Gupta","submitted_at":"2025-04-16T17:48:12Z","abstract_excerpt":"We tackle the novel problem of predicting 3D hand motion and contact maps (or Interaction Trajectories) given a single RGB view, action text, and a 3D contact point on the object as input. Our approach consists of (1) Interaction Codebook: a VQVAE model to learn a latent codebook of hand poses and contact points, effectively tokenizing interaction trajectories, (2) Interaction Predictor: a transformer-decoder module to predict the interaction trajectory from test time inputs by using an indexer module to retrieve a latent affordance from the learned codebook. To train our model, we develop a d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12284","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/2504.12284/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":"2504.12284","created_at":"2026-07-05T10:50:05.869474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12284v1","created_at":"2026-07-05T10:50:05.869474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12284","created_at":"2026-07-05T10:50:05.869474+00:00"},{"alias_kind":"pith_short_12","alias_value":"I73LUCKFHIM7","created_at":"2026-07-05T10:50:05.869474+00:00"},{"alias_kind":"pith_short_16","alias_value":"I73LUCKFHIM7PHWF","created_at":"2026-07-05T10:50:05.869474+00:00"},{"alias_kind":"pith_short_8","alias_value":"I73LUCKF","created_at":"2026-07-05T10:50:05.869474+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/I73LUCKFHIM7PHWFI5PCYMTLFO","json":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO.json","graph_json":"https://pith.science/api/pith-number/I73LUCKFHIM7PHWFI5PCYMTLFO/graph.json","events_json":"https://pith.science/api/pith-number/I73LUCKFHIM7PHWFI5PCYMTLFO/events.json","paper":"https://pith.science/paper/I73LUCKF"},"agent_actions":{"view_html":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO","download_json":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO.json","view_paper":"https://pith.science/paper/I73LUCKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12284&json=true","fetch_graph":"https://pith.science/api/pith-number/I73LUCKFHIM7PHWFI5PCYMTLFO/graph.json","fetch_events":"https://pith.science/api/pith-number/I73LUCKFHIM7PHWFI5PCYMTLFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO/action/storage_attestation","attest_author":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO/action/author_attestation","sign_citation":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO/action/citation_signature","submit_replication":"https://pith.science/pith/I73LUCKFHIM7PHWFI5PCYMTLFO/action/replication_record"}},"created_at":"2026-07-05T10:50:05.869474+00:00","updated_at":"2026-07-05T10:50:05.869474+00:00"}