{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:77AC3K6IUXLF44Y4IAQZP4G6RH","short_pith_number":"pith:77AC3K6I","schema_version":"1.0","canonical_sha256":"ffc02dabc8a5d65e731c402197f0de89c8ed7ffac30d95193631a63395184a37","source":{"kind":"arxiv","id":"2309.16524","version":2},"attestation_state":"computed","paper":{"title":"HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniel Sliwowski, Dongheui Lee, Esteve Valls Mascaro","submitted_at":"2023-09-28T15:34:49Z","abstract_excerpt":"Robots are becoming increasingly integrated into our lives, assisting us in various tasks. To ensure effective collaboration between humans and robots, it is essential that they understand our intentions and anticipate our actions. In this paper, we propose a Human-Object Interaction (HOI) anticipation framework for collaborative robots. We propose an efficient and robust transformer-based model to detect and anticipate HOIs from videos. This enhanced anticipation empowers robots to proactively assist humans, resulting in more efficient and intuitive collaborations. Our model outperforms state"},"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":"2309.16524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-28T15:34:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1d0de9774c7f64b7ad7dfa96319ce7056cb7ded3de94c665f34a7fdc06297c47","abstract_canon_sha256":"4e27f14056a3487f5980b46422450200b9b006fcbd2fe0a4c9ce8e8a012d3d3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:38.290530Z","signature_b64":"95gRPYAVEF3K8nSGm8nRjXHRZrNfBuIou5paX90VWQ/v7BSe57mZ4dmisSVdxgqKSycZTnJWGeCi/2iUaLq/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffc02dabc8a5d65e731c402197f0de89c8ed7ffac30d95193631a63395184a37","last_reissued_at":"2026-07-05T08:05:38.290051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:38.290051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniel Sliwowski, Dongheui Lee, Esteve Valls Mascaro","submitted_at":"2023-09-28T15:34:49Z","abstract_excerpt":"Robots are becoming increasingly integrated into our lives, assisting us in various tasks. To ensure effective collaboration between humans and robots, it is essential that they understand our intentions and anticipate our actions. In this paper, we propose a Human-Object Interaction (HOI) anticipation framework for collaborative robots. We propose an efficient and robust transformer-based model to detect and anticipate HOIs from videos. This enhanced anticipation empowers robots to proactively assist humans, resulting in more efficient and intuitive collaborations. Our model outperforms state"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16524","kind":"arxiv","version":2},"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/2309.16524/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":"2309.16524","created_at":"2026-07-05T08:05:38.290112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16524v2","created_at":"2026-07-05T08:05:38.290112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16524","created_at":"2026-07-05T08:05:38.290112+00:00"},{"alias_kind":"pith_short_12","alias_value":"77AC3K6IUXLF","created_at":"2026-07-05T08:05:38.290112+00:00"},{"alias_kind":"pith_short_16","alias_value":"77AC3K6IUXLF44Y4","created_at":"2026-07-05T08:05:38.290112+00:00"},{"alias_kind":"pith_short_8","alias_value":"77AC3K6I","created_at":"2026-07-05T08:05:38.290112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01368","citing_title":"Assistance Without Interruption: A Benchmark and LLM-based Framework for Non-Intrusive Human-Robot Assistance","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10397","citing_title":"Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH","json":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH.json","graph_json":"https://pith.science/api/pith-number/77AC3K6IUXLF44Y4IAQZP4G6RH/graph.json","events_json":"https://pith.science/api/pith-number/77AC3K6IUXLF44Y4IAQZP4G6RH/events.json","paper":"https://pith.science/paper/77AC3K6I"},"agent_actions":{"view_html":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH","download_json":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH.json","view_paper":"https://pith.science/paper/77AC3K6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16524&json=true","fetch_graph":"https://pith.science/api/pith-number/77AC3K6IUXLF44Y4IAQZP4G6RH/graph.json","fetch_events":"https://pith.science/api/pith-number/77AC3K6IUXLF44Y4IAQZP4G6RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH/action/storage_attestation","attest_author":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH/action/author_attestation","sign_citation":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH/action/citation_signature","submit_replication":"https://pith.science/pith/77AC3K6IUXLF44Y4IAQZP4G6RH/action/replication_record"}},"created_at":"2026-07-05T08:05:38.290112+00:00","updated_at":"2026-07-05T08:05:38.290112+00:00"}