{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RFF3HE2CYVH5UQZZBS4FC7DVRO","short_pith_number":"pith:RFF3HE2C","schema_version":"1.0","canonical_sha256":"894bb39342c54fda43390cb8517c758b84efdf18655f6a7498a503be70337dba","source":{"kind":"arxiv","id":"2604.11730","version":4},"attestation_state":"computed","paper":{"title":"Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Standard deep learning models show limited success recognizing ambivalence and hesitancy in videos, indicating that better methods for handling multimodal conflicts are needed.","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Lameiras Koerich, Eric Granger, Lorenzo Sia, Manuela Gonz\\'alez-Gonz\\'alez, Marco Pedersoli, Masoumeh Sharafi, Muhammad Haseeb Aslam, Muhammad Osama Zeeshan, Nicolas Richet, Simon L Bacon, Soufiane Belharbi","submitted_at":"2026-04-13T17:05:38Z","abstract_excerpt":"Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain healthy habits that improve medical outcomes. In-person interventions are costly and difficult to scale, especially in resource-limited regions. Digital health interventions offer a cost-effective approach, potentially supporting independent living and self-management. Automating such interventions, especially through machine learning, has recently gained considerable attention. Ambivalence and hesitancy (A/H) play a primary role for individuals to delay, avo"},"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":true},"canonical_record":{"source":{"id":"2604.11730","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T17:05:38Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"b72966544afcc83e8a57c69ab66d7ff2f848820db1ac353945a44605aa1765da","abstract_canon_sha256":"c7f7f843df43333e94e8e68d4d7eb893872b6b02f94b74b4ee849e8f73500137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:40.179948Z","signature_b64":"+1ZIwlzvJYyGvkpsc4WbWuvTww83Y02vWTFoc7BMELRBP8m1qfelFIOl3cHfuc/T6yKrG1dUelCyxQJsJ45mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"894bb39342c54fda43390cb8517c758b84efdf18655f6a7498a503be70337dba","last_reissued_at":"2026-07-07T02:18:40.179022Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:40.179022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Standard deep learning models show limited success recognizing ambivalence and hesitancy in videos, indicating that better methods for handling multimodal conflicts are needed.","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Lameiras Koerich, Eric Granger, Lorenzo Sia, Manuela Gonz\\'alez-Gonz\\'alez, Marco Pedersoli, Masoumeh Sharafi, Muhammad Haseeb Aslam, Muhammad Osama Zeeshan, Nicolas Richet, Simon L Bacon, Soufiane Belharbi","submitted_at":"2026-04-13T17:05:38Z","abstract_excerpt":"Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain healthy habits that improve medical outcomes. In-person interventions are costly and difficult to scale, especially in resource-limited regions. Digital health interventions offer a cost-effective approach, potentially supporting independent living and self-management. Automating such interventions, especially through machine learning, has recently gained considerable attention. Ambivalence and hesitancy (A/H) play a primary role for individuals to delay, avo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results show limited performance, suggesting that more adapted multi-modal models are required for accurate A/H recognition. Better methods for modeling spatio-temporal and multimodal fusion are necessary to leverage conflicts within/across modalities.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That standard deep learning architectures for video can capture subtle affective inconsistencies across and within modalities without major new adaptations for spatio-temporal fusion.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Multimodal deep learning for ambivalence/hesitancy recognition in videos yields limited results on the BAH dataset, highlighting the need for improved spatio-temporal and cross-modal fusion methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Standard deep learning models show limited success recognizing ambivalence and hesitancy in videos, indicating that better methods for handling multimodal conflicts are needed.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"986e596f1a587c237f369c7949e7ad6f8a12a04434657fc32bfd1330cc8af233"},"source":{"id":"2604.11730","kind":"arxiv","version":4},"verdict":{"id":"54ac16e9-2ebb-4196-af1c-71960c246511","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:56:49.245876Z","strongest_claim":"Our results show limited performance, suggesting that more adapted multi-modal models are required for accurate A/H recognition. Better methods for modeling spatio-temporal and multimodal fusion are necessary to leverage conflicts within/across modalities.","one_line_summary":"Multimodal deep learning for ambivalence/hesitancy recognition in videos yields limited results on the BAH dataset, highlighting the need for improved spatio-temporal and cross-modal fusion methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That standard deep learning architectures for video can capture subtle affective inconsistencies across and within modalities without major new adaptations for spatio-temporal fusion.","pith_extraction_headline":"Standard deep learning models show limited success recognizing ambivalence and hesitancy in videos, indicating that better methods for handling multimodal conflicts are needed."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11730/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":2,"snapshot_sha256":"d1b49c6209ccc2fb59020df247998ee36fef5a4d5f0c9454b423c66cb59c023e"},"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":"2604.11730","created_at":"2026-07-07T02:18:40.179149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.11730v4","created_at":"2026-07-07T02:18:40.179149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11730","created_at":"2026-07-07T02:18:40.179149+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFF3HE2CYVH5","created_at":"2026-07-07T02:18:40.179149+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFF3HE2CYVH5UQZZ","created_at":"2026-07-07T02:18:40.179149+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFF3HE2C","created_at":"2026-07-07T02:18:40.179149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO","json":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO.json","graph_json":"https://pith.science/api/pith-number/RFF3HE2CYVH5UQZZBS4FC7DVRO/graph.json","events_json":"https://pith.science/api/pith-number/RFF3HE2CYVH5UQZZBS4FC7DVRO/events.json","paper":"https://pith.science/paper/RFF3HE2C"},"agent_actions":{"view_html":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO","download_json":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO.json","view_paper":"https://pith.science/paper/RFF3HE2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.11730&json=true","fetch_graph":"https://pith.science/api/pith-number/RFF3HE2CYVH5UQZZBS4FC7DVRO/graph.json","fetch_events":"https://pith.science/api/pith-number/RFF3HE2CYVH5UQZZBS4FC7DVRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO/action/storage_attestation","attest_author":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO/action/author_attestation","sign_citation":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO/action/citation_signature","submit_replication":"https://pith.science/pith/RFF3HE2CYVH5UQZZBS4FC7DVRO/action/replication_record"}},"created_at":"2026-07-07T02:18:40.179149+00:00","updated_at":"2026-07-07T02:18:40.179149+00:00"}