{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7ZWUYLTOZWYS6ZH4W6FRMCDDMI","short_pith_number":"pith:7ZWUYLTO","schema_version":"1.0","canonical_sha256":"fe6d4c2e6ecdb12f64fcb78b1608636211fb76b29fb9191e4a6f78eb03d64656","source":{"kind":"arxiv","id":"2504.00839","version":2},"attestation_state":"computed","paper":{"title":"Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Andrey Rudenko, Lino Lerch, Luigi Palmieri, Marco Aiello, Sebastian Koch, Timo Ropinski, Yuchen Liu","submitted_at":"2025-04-01T14:28:19Z","abstract_excerpt":"Predicting human behavior in shared environments is crucial for safe and efficient human-robot interaction. Traditional data-driven methods to that end are pre-trained on domain-specific datasets, activity types, and prediction horizons. In contrast, the recent breakthroughs in Large Language Models (LLMs) promise open-ended cross-domain generalization to describe various human activities and make predictions in any context. In particular, Multimodal LLMs (MLLMs) are able to integrate information from various sources, achieving more contextual awareness and improved scene understanding. The di"},"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":"2504.00839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-01T14:28:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c86df13d5aef166f7db6fb5e4cbac007129442b3db07fa8bf7ec71071575a15","abstract_canon_sha256":"198a666376eb9c6aa943122952895a65d2c8ef3394683ff2ee63768c18eed8a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:43.677170Z","signature_b64":"MrOx30RskVI4bHADqig1arfRbYE22wUKOu4S0dumLan6g8XY9qyVcTTT/2LM6juo3+u9CZBQqXdcfK4JN0llCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe6d4c2e6ecdb12f64fcb78b1608636211fb76b29fb9191e4a6f78eb03d64656","last_reissued_at":"2026-07-05T11:25:43.676632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:43.676632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Andrey Rudenko, Lino Lerch, Luigi Palmieri, Marco Aiello, Sebastian Koch, Timo Ropinski, Yuchen Liu","submitted_at":"2025-04-01T14:28:19Z","abstract_excerpt":"Predicting human behavior in shared environments is crucial for safe and efficient human-robot interaction. Traditional data-driven methods to that end are pre-trained on domain-specific datasets, activity types, and prediction horizons. In contrast, the recent breakthroughs in Large Language Models (LLMs) promise open-ended cross-domain generalization to describe various human activities and make predictions in any context. In particular, Multimodal LLMs (MLLMs) are able to integrate information from various sources, achieving more contextual awareness and improved scene understanding. The di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00839","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/2504.00839/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":"2504.00839","created_at":"2026-07-05T11:25:43.676699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00839v2","created_at":"2026-07-05T11:25:43.676699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00839","created_at":"2026-07-05T11:25:43.676699+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZWUYLTOZWYS","created_at":"2026-07-05T11:25:43.676699+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZWUYLTOZWYS6ZH4","created_at":"2026-07-05T11:25:43.676699+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZWUYLTO","created_at":"2026-07-05T11:25:43.676699+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/7ZWUYLTOZWYS6ZH4W6FRMCDDMI","json":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI.json","graph_json":"https://pith.science/api/pith-number/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/graph.json","events_json":"https://pith.science/api/pith-number/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/events.json","paper":"https://pith.science/paper/7ZWUYLTO"},"agent_actions":{"view_html":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI","download_json":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI.json","view_paper":"https://pith.science/paper/7ZWUYLTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00839&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/action/storage_attestation","attest_author":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/action/author_attestation","sign_citation":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/action/citation_signature","submit_replication":"https://pith.science/pith/7ZWUYLTOZWYS6ZH4W6FRMCDDMI/action/replication_record"}},"created_at":"2026-07-05T11:25:43.676699+00:00","updated_at":"2026-07-05T11:25:43.676699+00:00"}