{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RFF3HE2CYVH5UQZZBS4FC7DVRO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c7f7f843df43333e94e8e68d4d7eb893872b6b02f94b74b4ee849e8f73500137","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T17:05:38Z","title_canon_sha256":"b72966544afcc83e8a57c69ab66d7ff2f848820db1ac353945a44605aa1765da"},"schema_version":"1.0","source":{"id":"2604.11730","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11730","created_at":"2026-07-07T02:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11730v4","created_at":"2026-07-07T02:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11730","created_at":"2026-07-07T02:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"RFF3HE2CYVH5","created_at":"2026-07-07T02:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"RFF3HE2CYVH5UQZZ","created_at":"2026-07-07T02:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"RFF3HE2C","created_at":"2026-07-07T02:18:40Z"}],"graph_snapshots":[{"event_id":"sha256:61f3bea0a22efc2a5d99b7ef46fcdd12f6dd60fae091a3c7d17228cde1bd8cea","target":"graph","created_at":"2026-07-07T02:18:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Standard deep learning models show limited success recognizing ambivalence and hesitancy in videos, indicating that better methods for handling multimodal conflicts are needed."}],"snapshot_sha256":"986e596f1a587c237f369c7949e7ad6f8a12a04434657fc32bfd1330cc8af233"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d1b49c6209ccc2fb59020df247998ee36fef5a4d5f0c9454b423c66cb59c023e"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.HC","cs.LG"],"headline":"Standard deep learning models show limited success recognizing ambivalence and hesitancy in videos, indicating that better methods for handling multimodal conflicts are needed.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T17:05:38Z","title":"Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11730","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-10T15:56:49.245876Z","id":"54ac16e9-2ebb-4196-af1c-71960c246511","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"54ac16e9-2ebb-4196-af1c-71960c246511"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4abdd7e5aecd5fac149b0d210d15e2ab7712cd0624768b0f77ae500b7d300a90","target":"record","created_at":"2026-07-07T02:18:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c7f7f843df43333e94e8e68d4d7eb893872b6b02f94b74b4ee849e8f73500137","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T17:05:38Z","title_canon_sha256":"b72966544afcc83e8a57c69ab66d7ff2f848820db1ac353945a44605aa1765da"},"schema_version":"1.0","source":{"id":"2604.11730","kind":"arxiv","version":4}},"canonical_sha256":"894bb39342c54fda43390cb8517c758b84efdf18655f6a7498a503be70337dba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"894bb39342c54fda43390cb8517c758b84efdf18655f6a7498a503be70337dba","first_computed_at":"2026-07-07T02:18:40.179022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:40.179022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+1ZIwlzvJYyGvkpsc4WbWuvTww83Y02vWTFoc7BMELRBP8m1qfelFIOl3cHfuc/T6yKrG1dUelCyxQJsJ45mBA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:40.179948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11730","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4abdd7e5aecd5fac149b0d210d15e2ab7712cd0624768b0f77ae500b7d300a90","sha256:61f3bea0a22efc2a5d99b7ef46fcdd12f6dd60fae091a3c7d17228cde1bd8cea"],"state_sha256":"892cb6a2c2710dd2b08217de7c57cfb957805c7c4c64b63fca5e7d9c6a36857b"}