{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J7DS2B2GZI2AENS6TC7CELRFKO","short_pith_number":"pith:J7DS2B2G","schema_version":"1.0","canonical_sha256":"4fc72d0746ca3402365e98be222e25538343d95875c67453a9308f7b4cd7d476","source":{"kind":"arxiv","id":"2505.15928","version":1},"attestation_state":"computed","paper":{"title":"ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fernando Lozano, Tony Montes","submitted_at":"2025-05-21T18:32:43Z","abstract_excerpt":"Recent advancements in Video Question Answering (VideoQA) have introduced LLM-based agents, modular frameworks, and procedural solutions, yielding promising results. These systems use dynamic agents and memory-based mechanisms to break down complex tasks and refine answers. However, significant improvements remain in tracking objects for grounding over time and decision-making based on reasoning to better align object references with language model outputs, as newer models get better at both tasks. This work presents an LLM-brained agent for zero-shot Video Question Answering (VideoQA) that co"},"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":"2505.15928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T18:32:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"220be43e04f9e15f7be2f823321fa123ae189000135177344702a157a5a501e9","abstract_canon_sha256":"ca293723b33e019e73b7461dd8ae22e2233d684976bb3d260471cb29cb189ac3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:27.450830Z","signature_b64":"abnPJRE0DbVhmneDMHLjrArmKZCD7P1i6h79lEoVRCR3IeqUSoFE7U0GozuM4gKn+0rZ9X/MxacDcs7zY/ApCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fc72d0746ca3402365e98be222e25538343d95875c67453a9308f7b4cd7d476","last_reissued_at":"2026-07-05T11:07:27.450333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:27.450333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fernando Lozano, Tony Montes","submitted_at":"2025-05-21T18:32:43Z","abstract_excerpt":"Recent advancements in Video Question Answering (VideoQA) have introduced LLM-based agents, modular frameworks, and procedural solutions, yielding promising results. These systems use dynamic agents and memory-based mechanisms to break down complex tasks and refine answers. However, significant improvements remain in tracking objects for grounding over time and decision-making based on reasoning to better align object references with language model outputs, as newer models get better at both tasks. This work presents an LLM-brained agent for zero-shot Video Question Answering (VideoQA) that co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15928","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/2505.15928/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":"2505.15928","created_at":"2026-07-05T11:07:27.450405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15928v1","created_at":"2026-07-05T11:07:27.450405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15928","created_at":"2026-07-05T11:07:27.450405+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7DS2B2GZI2A","created_at":"2026-07-05T11:07:27.450405+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7DS2B2GZI2AENS6","created_at":"2026-07-05T11:07:27.450405+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7DS2B2G","created_at":"2026-07-05T11:07:27.450405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01469","citing_title":"A Cost-Aware, Paired Protocol for Auditing Dynamic Tool Synthesis in Agentic Video Question Answering","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":214,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO","json":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO.json","graph_json":"https://pith.science/api/pith-number/J7DS2B2GZI2AENS6TC7CELRFKO/graph.json","events_json":"https://pith.science/api/pith-number/J7DS2B2GZI2AENS6TC7CELRFKO/events.json","paper":"https://pith.science/paper/J7DS2B2G"},"agent_actions":{"view_html":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO","download_json":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO.json","view_paper":"https://pith.science/paper/J7DS2B2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15928&json=true","fetch_graph":"https://pith.science/api/pith-number/J7DS2B2GZI2AENS6TC7CELRFKO/graph.json","fetch_events":"https://pith.science/api/pith-number/J7DS2B2GZI2AENS6TC7CELRFKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/action/storage_attestation","attest_author":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/action/author_attestation","sign_citation":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/action/citation_signature","submit_replication":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/action/replication_record"}},"created_at":"2026-07-05T11:07:27.450405+00:00","updated_at":"2026-07-05T11:07:27.450405+00:00"}