{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:77X2646FYXIMB7N4CDRNGEMWDS","short_pith_number":"pith:77X2646F","schema_version":"1.0","canonical_sha256":"ffefaf73c5c5d0c0fdbc10e2d311961cbad5b11f0c5570e2fc529b9672b40266","source":{"kind":"arxiv","id":"2503.16451","version":1},"attestation_state":"computed","paper":{"title":"Think-Then-React: Towards Unconstrained Human Action-to-Reaction Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.HC","authors_text":"BoYuan Li, Chuhao Jin, Ruihua Song, Wenbing Huang, Wenhui Tan, Xiting Wang","submitted_at":"2025-02-19T12:14:38Z","abstract_excerpt":"Modeling human-like action-to-reaction generation has significant real-world applications, like human-robot interaction and games. Despite recent advancements in single-person motion generation, it is still challenging to well handle action-to-reaction generation, due to the difficulty of directly predicting reaction from action sequence without prompts, and the absence of a unified representation that effectively encodes multi-person motion. To address these challenges, we introduce Think-Then-React (TTR), a large language-model-based framework designed to generate human-like reactions. First"},"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":"2503.16451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-02-19T12:14:38Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"745e054a20e385a5a7b6fdfba40bf29f96d5186c088137c371dafbb2f6ba3327","abstract_canon_sha256":"b078dd7b4ffb6e463168f21b495a48a8f999f3cbf37627a254c562f98b055aff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:41.108840Z","signature_b64":"GERg1rvNA+w3vsXD4tsiZbr894e9/lqZZjjxTWPeuU568yC/kId8tKwT3sjNMpgfRHBuGokb+NKJQ9Y8ecHIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffefaf73c5c5d0c0fdbc10e2d311961cbad5b11f0c5570e2fc529b9672b40266","last_reissued_at":"2026-07-05T10:36:41.108354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:41.108354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think-Then-React: Towards Unconstrained Human Action-to-Reaction Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.HC","authors_text":"BoYuan Li, Chuhao Jin, Ruihua Song, Wenbing Huang, Wenhui Tan, Xiting Wang","submitted_at":"2025-02-19T12:14:38Z","abstract_excerpt":"Modeling human-like action-to-reaction generation has significant real-world applications, like human-robot interaction and games. Despite recent advancements in single-person motion generation, it is still challenging to well handle action-to-reaction generation, due to the difficulty of directly predicting reaction from action sequence without prompts, and the absence of a unified representation that effectively encodes multi-person motion. To address these challenges, we introduce Think-Then-React (TTR), a large language-model-based framework designed to generate human-like reactions. First"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16451","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/2503.16451/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":"2503.16451","created_at":"2026-07-05T10:36:41.108410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16451v1","created_at":"2026-07-05T10:36:41.108410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16451","created_at":"2026-07-05T10:36:41.108410+00:00"},{"alias_kind":"pith_short_12","alias_value":"77X2646FYXIM","created_at":"2026-07-05T10:36:41.108410+00:00"},{"alias_kind":"pith_short_16","alias_value":"77X2646FYXIMB7N4","created_at":"2026-07-05T10:36:41.108410+00:00"},{"alias_kind":"pith_short_8","alias_value":"77X2646F","created_at":"2026-07-05T10:36:41.108410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21059","citing_title":"DEFENGRAPH: Knowledge Graph-Enhanced LLMs for Blue Team Cyber Defense","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS","json":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS.json","graph_json":"https://pith.science/api/pith-number/77X2646FYXIMB7N4CDRNGEMWDS/graph.json","events_json":"https://pith.science/api/pith-number/77X2646FYXIMB7N4CDRNGEMWDS/events.json","paper":"https://pith.science/paper/77X2646F"},"agent_actions":{"view_html":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS","download_json":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS.json","view_paper":"https://pith.science/paper/77X2646F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16451&json=true","fetch_graph":"https://pith.science/api/pith-number/77X2646FYXIMB7N4CDRNGEMWDS/graph.json","fetch_events":"https://pith.science/api/pith-number/77X2646FYXIMB7N4CDRNGEMWDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS/action/storage_attestation","attest_author":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS/action/author_attestation","sign_citation":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS/action/citation_signature","submit_replication":"https://pith.science/pith/77X2646FYXIMB7N4CDRNGEMWDS/action/replication_record"}},"created_at":"2026-07-05T10:36:41.108410+00:00","updated_at":"2026-07-05T10:36:41.108410+00:00"}