{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MOTN2NH4VL3P3IH66YPNAZTUSC","short_pith_number":"pith:MOTN2NH4","schema_version":"1.0","canonical_sha256":"63a6dd34fcaaf6fda0fef61ed0667490a18fb0ad4bc57e21578748ad85caac79","source":{"kind":"arxiv","id":"2605.21917","version":1},"attestation_state":"computed","paper":{"title":"MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Zhang, Tian Zheng, Tomasz Kornuta, Vidya Murali, Wanting Jiang","submitted_at":"2026-05-21T02:44:27Z","abstract_excerpt":"Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support. We present MAVEN (Multi-stage Agentic Video Event aNnotation), a multi-stage agentic pipeline that turns raw videos into multi-task training data with Chain-of-Thought (CoT) reasoning traces, organized around a designated Event of Focus. At its core, MAVEN synthesizes a Multi-Scale Spatio-Temporal Event Description (MSTED) from three complementary caption level"},"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":"2605.21917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T02:44:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4be6e52aa63d1cc2cd78104dd34f1f82abbc09bc830de7c02214c496e323f24","abstract_canon_sha256":"443885ba5bbdbd1cbf8f1f8c102fa3ac662f3cc84bbb2c17717c8182e6610c91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:14.562864Z","signature_b64":"qW8BgT9pS39bnMLgm5Jj7rlSpAqsFMoyCVVuN3fCE8GnWJaW29ur0VFLff1w5h8SpHx0T8i8jFmFTXPv1OoKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63a6dd34fcaaf6fda0fef61ed0667490a18fb0ad4bc57e21578748ad85caac79","last_reissued_at":"2026-05-22T01:04:14.561991Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:14.561991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Zhang, Tian Zheng, Tomasz Kornuta, Vidya Murali, Wanting Jiang","submitted_at":"2026-05-21T02:44:27Z","abstract_excerpt":"Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support. We present MAVEN (Multi-stage Agentic Video Event aNnotation), a multi-stage agentic pipeline that turns raw videos into multi-task training data with Chain-of-Thought (CoT) reasoning traces, organized around a designated Event of Focus. At its core, MAVEN synthesizes a Multi-Scale Spatio-Temporal Event Description (MSTED) from three complementary caption level"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21917","kind":"arxiv","version":1},"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/2605.21917/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":"2605.21917","created_at":"2026-05-22T01:04:14.562135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21917v1","created_at":"2026-05-22T01:04:14.562135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21917","created_at":"2026-05-22T01:04:14.562135+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOTN2NH4VL3P","created_at":"2026-05-22T01:04:14.562135+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOTN2NH4VL3P3IH6","created_at":"2026-05-22T01:04:14.562135+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOTN2NH4","created_at":"2026-05-22T01:04:14.562135+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/MOTN2NH4VL3P3IH66YPNAZTUSC","json":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC.json","graph_json":"https://pith.science/api/pith-number/MOTN2NH4VL3P3IH66YPNAZTUSC/graph.json","events_json":"https://pith.science/api/pith-number/MOTN2NH4VL3P3IH66YPNAZTUSC/events.json","paper":"https://pith.science/paper/MOTN2NH4"},"agent_actions":{"view_html":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC","download_json":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC.json","view_paper":"https://pith.science/paper/MOTN2NH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21917&json=true","fetch_graph":"https://pith.science/api/pith-number/MOTN2NH4VL3P3IH66YPNAZTUSC/graph.json","fetch_events":"https://pith.science/api/pith-number/MOTN2NH4VL3P3IH66YPNAZTUSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC/action/storage_attestation","attest_author":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC/action/author_attestation","sign_citation":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC/action/citation_signature","submit_replication":"https://pith.science/pith/MOTN2NH4VL3P3IH66YPNAZTUSC/action/replication_record"}},"created_at":"2026-05-22T01:04:14.562135+00:00","updated_at":"2026-05-22T01:04:14.562135+00:00"}