{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VHA7BAXH3SZKQS7LJXKGKAIQKA","short_pith_number":"pith:VHA7BAXH","schema_version":"1.0","canonical_sha256":"a9c1f082e7dcb2a84beb4dd4650110500cdc5317481d01ed496b02cd7752b897","source":{"kind":"arxiv","id":"2410.16259","version":1},"attestation_state":"computed","paper":{"title":"Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrea Bajcsy, Angjoo Kanazawa, Gengshan Yang, Shunsuke Saito","submitted_at":"2024-10-21T17:57:50Z","abstract_excerpt":"We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on marker-based tracking and multiview cameras, ATS learns natural behaviors of animal and human agents non-invasively through video observations recorded over a long time-span (e.g., a month) in a single environment. Modeling 3D behavior of an agent requires persistent 3D tracking (e.g., knowing which point corresponds to which) over a long time period. To obtain such data, we develop a coarse-to-fine registration met"},"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":"2410.16259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T17:57:50Z","cross_cats_sorted":["cs.GR","cs.RO"],"title_canon_sha256":"571965e43490a16c96e4f699bf8310db0604de10f7eb6cc188a7f14ccfa6bb0b","abstract_canon_sha256":"cbfd43e54a2cb93ed57151f72b041a3eaca10dd8073efd99c36f36f6a4a31815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:32.078388Z","signature_b64":"e2NmGdgn7LydkxtBumrggaAmrDZJyho382abeIt1qVJVhAKG71QqjpQwNsVPow0TFfv44vKxLSm4OvsWP2IZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9c1f082e7dcb2a84beb4dd4650110500cdc5317481d01ed496b02cd7752b897","last_reissued_at":"2026-07-05T09:23:32.077942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:32.077942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrea Bajcsy, Angjoo Kanazawa, Gengshan Yang, Shunsuke Saito","submitted_at":"2024-10-21T17:57:50Z","abstract_excerpt":"We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on marker-based tracking and multiview cameras, ATS learns natural behaviors of animal and human agents non-invasively through video observations recorded over a long time-span (e.g., a month) in a single environment. Modeling 3D behavior of an agent requires persistent 3D tracking (e.g., knowing which point corresponds to which) over a long time period. To obtain such data, we develop a coarse-to-fine registration met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16259","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/2410.16259/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":"2410.16259","created_at":"2026-07-05T09:23:32.078002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16259v1","created_at":"2026-07-05T09:23:32.078002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16259","created_at":"2026-07-05T09:23:32.078002+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHA7BAXH3SZK","created_at":"2026-07-05T09:23:32.078002+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHA7BAXH3SZKQS7L","created_at":"2026-07-05T09:23:32.078002+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHA7BAXH","created_at":"2026-07-05T09:23:32.078002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12393","citing_title":"Towards Affordance-Aware Articulation Synthesis for Rigged Objects","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA","json":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA.json","graph_json":"https://pith.science/api/pith-number/VHA7BAXH3SZKQS7LJXKGKAIQKA/graph.json","events_json":"https://pith.science/api/pith-number/VHA7BAXH3SZKQS7LJXKGKAIQKA/events.json","paper":"https://pith.science/paper/VHA7BAXH"},"agent_actions":{"view_html":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA","download_json":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA.json","view_paper":"https://pith.science/paper/VHA7BAXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16259&json=true","fetch_graph":"https://pith.science/api/pith-number/VHA7BAXH3SZKQS7LJXKGKAIQKA/graph.json","fetch_events":"https://pith.science/api/pith-number/VHA7BAXH3SZKQS7LJXKGKAIQKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA/action/storage_attestation","attest_author":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA/action/author_attestation","sign_citation":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA/action/citation_signature","submit_replication":"https://pith.science/pith/VHA7BAXH3SZKQS7LJXKGKAIQKA/action/replication_record"}},"created_at":"2026-07-05T09:23:32.078002+00:00","updated_at":"2026-07-05T09:23:32.078002+00:00"}