{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MKXZNUGL6EHBVUWWGHJSXWUXO5","short_pith_number":"pith:MKXZNUGL","canonical_record":{"source":{"id":"2407.01907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T03:13:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99bb84667706bbbf15dad991ba5b698309855f2dd12f85c99bb837d4c4c00c88","abstract_canon_sha256":"ba9c9d6cfdc6e643249909e28e76d4e9adc9e496cff4315c81ef1bf2595ac2d9"},"schema_version":"1.0"},"canonical_sha256":"62af96d0cbf10e1ad2d631d32bda97777739a93135080a429c487663b34faf9d","source":{"kind":"arxiv","id":"2407.01907","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01907","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01907v1","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01907","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"MKXZNUGL6EHB","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_16","alias_value":"MKXZNUGL6EHBVUWW","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_8","alias_value":"MKXZNUGL","created_at":"2026-07-05T08:39:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MKXZNUGL6EHBVUWWGHJSXWUXO5","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T03:13:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99bb84667706bbbf15dad991ba5b698309855f2dd12f85c99bb837d4c4c00c88","abstract_canon_sha256":"ba9c9d6cfdc6e643249909e28e76d4e9adc9e496cff4315c81ef1bf2595ac2d9"},"schema_version":"1.0"},"canonical_sha256":"62af96d0cbf10e1ad2d631d32bda97777739a93135080a429c487663b34faf9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:07.064191Z","signature_b64":"6OcoZDIugG4H9Q8cQcLml3o9EDCMP/nzMEu9h+ptd6z0taj4ZKW4+X0iNf85a6r4MPcshVmmuXW9a9DItAj/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62af96d0cbf10e1ad2d631d32bda97777739a93135080a429c487663b34faf9d","last_reissued_at":"2026-07-05T08:39:07.063653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:07.063653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01907","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":"2026-07-05T08:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVz/40BKFUMLuvO4opqKzn037dzFQL/lIgP1cELxnOem3X9PEfdLWB3rEwjc+54jsKYIXHqvRnWNvxv9cfysAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:43:24.378997Z"},"content_sha256":"9d87147dea8385045edb21986aeb11375b13fd630eccb53367fa7d8c14527368","schema_version":"1.0","event_id":"sha256:9d87147dea8385045edb21986aeb11375b13fd630eccb53367fa7d8c14527368"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MKXZNUGL6EHBVUWWGHJSXWUXO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Solution for the ICCV 2023 Perception Test Challenge 2023 -- Task 6 -- Grounded videoQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dian Chao, Hailiang Zhang, Yang Yang, Zhihao Guan","submitted_at":"2024-07-02T03:13:27Z","abstract_excerpt":"In this paper, we introduce a grounded video question-answering solution. Our research reveals that the fixed official baseline method for video question answering involves two main steps: visual grounding and object tracking. However, a significant challenge emerges during the initial step, where selected frames may lack clearly identifiable target objects. Furthermore, single images cannot address questions like \"Track the container from which the person pours the first time.\" To tackle this issue, we propose an alternative two-stage approach:(1) First, we leverage the VALOR model to answer "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01907","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/2407.01907/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":"2026-07-05T08:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1/4jFCr7M8BMCZyXggVP4QX5tK2sKbaWzpDZfD791mmv6PmSNr+eX28p6jDMw8VTg0RDAjdTXJXS+UEVeXRcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:43:24.379557Z"},"content_sha256":"95c054ca588f37c7468221feecdfa755735491dce0524e1d4462b495b77ef505","schema_version":"1.0","event_id":"sha256:95c054ca588f37c7468221feecdfa755735491dce0524e1d4462b495b77ef505"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKXZNUGL6EHBVUWWGHJSXWUXO5/bundle.json","state_url":"https://pith.science/pith/MKXZNUGL6EHBVUWWGHJSXWUXO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKXZNUGL6EHBVUWWGHJSXWUXO5/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":"2026-08-20T06:43:24Z","links":{"resolver":"https://pith.science/pith/MKXZNUGL6EHBVUWWGHJSXWUXO5","bundle":"https://pith.science/pith/MKXZNUGL6EHBVUWWGHJSXWUXO5/bundle.json","state":"https://pith.science/pith/MKXZNUGL6EHBVUWWGHJSXWUXO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKXZNUGL6EHBVUWWGHJSXWUXO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MKXZNUGL6EHBVUWWGHJSXWUXO5","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":"ba9c9d6cfdc6e643249909e28e76d4e9adc9e496cff4315c81ef1bf2595ac2d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T03:13:27Z","title_canon_sha256":"99bb84667706bbbf15dad991ba5b698309855f2dd12f85c99bb837d4c4c00c88"},"schema_version":"1.0","source":{"id":"2407.01907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01907","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01907v1","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01907","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"MKXZNUGL6EHB","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_16","alias_value":"MKXZNUGL6EHBVUWW","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_8","alias_value":"MKXZNUGL","created_at":"2026-07-05T08:39:07Z"}],"graph_snapshots":[{"event_id":"sha256:95c054ca588f37c7468221feecdfa755735491dce0524e1d4462b495b77ef505","target":"graph","created_at":"2026-07-05T08:39:07Z","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/2407.01907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a grounded video question-answering solution. Our research reveals that the fixed official baseline method for video question answering involves two main steps: visual grounding and object tracking. However, a significant challenge emerges during the initial step, where selected frames may lack clearly identifiable target objects. Furthermore, single images cannot address questions like \"Track the container from which the person pours the first time.\" To tackle this issue, we propose an alternative two-stage approach:(1) First, we leverage the VALOR model to answer ","authors_text":"Dian Chao, Hailiang Zhang, Yang Yang, Zhihao Guan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T03:13:27Z","title":"The Solution for the ICCV 2023 Perception Test Challenge 2023 -- Task 6 -- Grounded videoQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01907","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":"sha256:9d87147dea8385045edb21986aeb11375b13fd630eccb53367fa7d8c14527368","target":"record","created_at":"2026-07-05T08:39:07Z","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":"ba9c9d6cfdc6e643249909e28e76d4e9adc9e496cff4315c81ef1bf2595ac2d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T03:13:27Z","title_canon_sha256":"99bb84667706bbbf15dad991ba5b698309855f2dd12f85c99bb837d4c4c00c88"},"schema_version":"1.0","source":{"id":"2407.01907","kind":"arxiv","version":1}},"canonical_sha256":"62af96d0cbf10e1ad2d631d32bda97777739a93135080a429c487663b34faf9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62af96d0cbf10e1ad2d631d32bda97777739a93135080a429c487663b34faf9d","first_computed_at":"2026-07-05T08:39:07.063653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:07.063653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6OcoZDIugG4H9Q8cQcLml3o9EDCMP/nzMEu9h+ptd6z0taj4ZKW4+X0iNf85a6r4MPcshVmmuXW9a9DItAj/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:07.064191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d87147dea8385045edb21986aeb11375b13fd630eccb53367fa7d8c14527368","sha256:95c054ca588f37c7468221feecdfa755735491dce0524e1d4462b495b77ef505"],"state_sha256":"7e44b0c2c5fd7035de064682eb3d5565de08cea6d4156ef5609bc7a6d44de7e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdbuSuyrdM0+O+vY0z3w8IrdkO09VL0WV1XtkrwjAFyZzJ2DdZ2699rS6MFLUnD9zzoogB6cKKpx5iScrEN1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:43:24.385221Z","bundle_sha256":"0e64351dcf071bf25e9b2b77299512c5c238191f461af7c62423b7ef93fea375"}}