{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XZ6YH37JZBEVVXT7HA5E3WATQR","short_pith_number":"pith:XZ6YH37J","schema_version":"1.0","canonical_sha256":"be7d83efe9c8495ade7f383a4dd81384603da4e2e939e12a3e49bd1f0685540f","source":{"kind":"arxiv","id":"2409.15867","version":5},"attestation_state":"computed","paper":{"title":"In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abdul Ahad, Ammar Anwar, Evangelos Chatzaroulas, Hamzah Azeem, Janusz Marecki, Luc McCutcheon, Moucheng Xu","submitted_at":"2024-09-24T08:41:01Z","abstract_excerpt":"A Standard Operating Procedure (SOP) defines a low-level, step-by-step written guide for a business software workflow. SOP generation is a crucial step towards automating end-to-end software workflows. Manually creating SOPs can be time-consuming. Recent advancements in large video-language models offer the potential for automating SOP generation by analyzing recordings of human demonstrations. However, current large video-language models face challenges with zero-shot SOP generation. In this work, we first explore in-context learning with video-language models for SOP generation. We then prop"},"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":"2409.15867","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-24T08:41:01Z","cross_cats_sorted":[],"title_canon_sha256":"01cdb2dcf4aa8301b04ee0966bb3f224ff70480fd745fadc3efa87c71d07abe3","abstract_canon_sha256":"a6fe595a3bb7bad310e3ee94c488f1be571580f93200389422689c09a769fea2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:12.267982Z","signature_b64":"4Vdw5kIjL3Y7Y/itdTgBoDgPYOQ3EBh/gQ4tC8BYGjFwztWDDpPDaZCZelXViETOqnLPR6XgolY0LvY/Oc/EBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be7d83efe9c8495ade7f383a4dd81384603da4e2e939e12a3e49bd1f0685540f","last_reissued_at":"2026-07-05T09:23:12.267591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:12.267591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abdul Ahad, Ammar Anwar, Evangelos Chatzaroulas, Hamzah Azeem, Janusz Marecki, Luc McCutcheon, Moucheng Xu","submitted_at":"2024-09-24T08:41:01Z","abstract_excerpt":"A Standard Operating Procedure (SOP) defines a low-level, step-by-step written guide for a business software workflow. SOP generation is a crucial step towards automating end-to-end software workflows. Manually creating SOPs can be time-consuming. Recent advancements in large video-language models offer the potential for automating SOP generation by analyzing recordings of human demonstrations. However, current large video-language models face challenges with zero-shot SOP generation. In this work, we first explore in-context learning with video-language models for SOP generation. We then prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15867","kind":"arxiv","version":5},"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/2409.15867/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":"2409.15867","created_at":"2026-07-05T09:23:12.267648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15867v5","created_at":"2026-07-05T09:23:12.267648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15867","created_at":"2026-07-05T09:23:12.267648+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZ6YH37JZBEV","created_at":"2026-07-05T09:23:12.267648+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZ6YH37JZBEVVXT7","created_at":"2026-07-05T09:23:12.267648+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZ6YH37J","created_at":"2026-07-05T09:23:12.267648+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/XZ6YH37JZBEVVXT7HA5E3WATQR","json":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR.json","graph_json":"https://pith.science/api/pith-number/XZ6YH37JZBEVVXT7HA5E3WATQR/graph.json","events_json":"https://pith.science/api/pith-number/XZ6YH37JZBEVVXT7HA5E3WATQR/events.json","paper":"https://pith.science/paper/XZ6YH37J"},"agent_actions":{"view_html":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR","download_json":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR.json","view_paper":"https://pith.science/paper/XZ6YH37J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15867&json=true","fetch_graph":"https://pith.science/api/pith-number/XZ6YH37JZBEVVXT7HA5E3WATQR/graph.json","fetch_events":"https://pith.science/api/pith-number/XZ6YH37JZBEVVXT7HA5E3WATQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR/action/storage_attestation","attest_author":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR/action/author_attestation","sign_citation":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR/action/citation_signature","submit_replication":"https://pith.science/pith/XZ6YH37JZBEVVXT7HA5E3WATQR/action/replication_record"}},"created_at":"2026-07-05T09:23:12.267648+00:00","updated_at":"2026-07-05T09:23:12.267648+00:00"}