{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J7DS2B2GZI2AENS6TC7CELRFKO","short_pith_number":"pith:J7DS2B2G","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"},"canonical_sha256":"4fc72d0746ca3402365e98be222e25538343d95875c67453a9308f7b4cd7d476","source":{"kind":"arxiv","id":"2505.15928","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15928","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15928v1","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15928","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"J7DS2B2GZI2A","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"J7DS2B2GZI2AENS6","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"J7DS2B2G","created_at":"2026-07-05T11:07:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J7DS2B2GZI2AENS6TC7CELRFKO","target":"record","payload":{"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"},"canonical_sha256":"4fc72d0746ca3402365e98be222e25538343d95875c67453a9308f7b4cd7d476","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"},"source_kind":"arxiv","source_id":"2505.15928","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k0YTCgQ1ApI4I/Oro7dyBvxieoZr5MR/9X6VSq+ezvdd8LetzjhLuff9ZeGA6hC3945TGai7r/UDbhCax+n8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:28:44.543271Z"},"content_sha256":"341a407760636597b428f2306614a2a595ddb9ad275d78314a6ae52ffc056061","schema_version":"1.0","event_id":"sha256:341a407760636597b428f2306614a2a595ddb9ad275d78314a6ae52ffc056061"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J7DS2B2GZI2AENS6TC7CELRFKO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFzZBcoTaYPo/W32MpJYNVJwF37I+6L+WPXC/OhMtjWbHz1p5BgG8ZYjbPuhm7qg6yS7pMtvGHbI/Vz2pYSbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:28:44.543672Z"},"content_sha256":"0f15a0909e535dab5bf107ad038c75cd16bb1d7cf53a7ed15984c3ae7f194f72","schema_version":"1.0","event_id":"sha256:0f15a0909e535dab5bf107ad038c75cd16bb1d7cf53a7ed15984c3ae7f194f72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/bundle.json","state_url":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J7DS2B2GZI2AENS6TC7CELRFKO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T13:28:44Z","links":{"resolver":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO","bundle":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/bundle.json","state":"https://pith.science/pith/J7DS2B2GZI2AENS6TC7CELRFKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J7DS2B2GZI2AENS6TC7CELRFKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J7DS2B2GZI2AENS6TC7CELRFKO","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":"ca293723b33e019e73b7461dd8ae22e2233d684976bb3d260471cb29cb189ac3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T18:32:43Z","title_canon_sha256":"220be43e04f9e15f7be2f823321fa123ae189000135177344702a157a5a501e9"},"schema_version":"1.0","source":{"id":"2505.15928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15928","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15928v1","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15928","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"J7DS2B2GZI2A","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"J7DS2B2GZI2AENS6","created_at":"2026-07-05T11:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"J7DS2B2G","created_at":"2026-07-05T11:07:27Z"}],"graph_snapshots":[{"event_id":"sha256:0f15a0909e535dab5bf107ad038c75cd16bb1d7cf53a7ed15984c3ae7f194f72","target":"graph","created_at":"2026-07-05T11:07:27Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.15928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fernando Lozano, Tony Montes","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T18:32:43Z","title":"ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15928","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:341a407760636597b428f2306614a2a595ddb9ad275d78314a6ae52ffc056061","target":"record","created_at":"2026-07-05T11:07:27Z","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":"ca293723b33e019e73b7461dd8ae22e2233d684976bb3d260471cb29cb189ac3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T18:32:43Z","title_canon_sha256":"220be43e04f9e15f7be2f823321fa123ae189000135177344702a157a5a501e9"},"schema_version":"1.0","source":{"id":"2505.15928","kind":"arxiv","version":1}},"canonical_sha256":"4fc72d0746ca3402365e98be222e25538343d95875c67453a9308f7b4cd7d476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fc72d0746ca3402365e98be222e25538343d95875c67453a9308f7b4cd7d476","first_computed_at":"2026-07-05T11:07:27.450333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:27.450333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"abnPJRE0DbVhmneDMHLjrArmKZCD7P1i6h79lEoVRCR3IeqUSoFE7U0GozuM4gKn+0rZ9X/MxacDcs7zY/ApCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:27.450830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:341a407760636597b428f2306614a2a595ddb9ad275d78314a6ae52ffc056061","sha256:0f15a0909e535dab5bf107ad038c75cd16bb1d7cf53a7ed15984c3ae7f194f72"],"state_sha256":"4c551e87af6d88030851ca927bbfc67a704b1b4be79c92cf374571a48bd9bf66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfAQHAQFUTR0NcVG981bjlz7NmuAjVURMp1tX/Z2v6603tcGbQwsqaINlQr2m4OhJP/X3Z4lumDr4+V5UizLDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:28:44.545733Z","bundle_sha256":"c195340395dd048fa38ebc418b53ec79cf6483bd40a21a2be46cf687ddbce6d6"}}