{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BDHQXFVJ6J4C2APDBQYE3RDJNQ","short_pith_number":"pith:BDHQXFVJ","canonical_record":{"source":{"id":"2406.15771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T07:20:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc5d3b16a1bb82860451fb805b58cc43cb1d6e94bffea70839437579a86a49e0","abstract_canon_sha256":"cece7b725d605e2125fd25692f65d21eefd9e098627779ef4a876fce0d8842a0"},"schema_version":"1.0"},"canonical_sha256":"08cf0b96a9f2782d01e30c304dc4696c2d43c4996de311cbf81616b86ed352a7","source":{"kind":"arxiv","id":"2406.15771","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15771","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15771v2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15771","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"BDHQXFVJ6J4C","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"BDHQXFVJ6J4C2APD","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"BDHQXFVJ","created_at":"2026-07-05T09:27:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BDHQXFVJ6J4C2APDBQYE3RDJNQ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T07:20:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc5d3b16a1bb82860451fb805b58cc43cb1d6e94bffea70839437579a86a49e0","abstract_canon_sha256":"cece7b725d605e2125fd25692f65d21eefd9e098627779ef4a876fce0d8842a0"},"schema_version":"1.0"},"canonical_sha256":"08cf0b96a9f2782d01e30c304dc4696c2d43c4996de311cbf81616b86ed352a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:23.613440Z","signature_b64":"AXAImiwD6+jHYe+6FDFrl4sJo4o8m+JW+Dz9BwquK7DOGwRnR7M/HmiVW+x3NZ8tZ8EgGnOV1A2epxBVBTR/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08cf0b96a9f2782d01e30c304dc4696c2d43c4996de311cbf81616b86ed352a7","last_reissued_at":"2026-07-05T09:27:23.612995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:23.612995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15771","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YWvxYp1OE0A7tnQWyDuLWBpX3fCOknTx2zSgeZWKnQP/RaSLdzRFlxvFfu6gZ2S90Ypxjdw8uEIUW+D+LTY6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:20:25.473434Z"},"content_sha256":"7f83fd8ea83d884f307c2187249fcb0157e2b082b68df69df3b9cc80f0cafebf","schema_version":"1.0","event_id":"sha256:7f83fd8ea83d884f307c2187249fcb0157e2b082b68df69df3b9cc80f0cafebf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BDHQXFVJ6J4C2APDBQYE3RDJNQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HCQA @ Ego4D EgoSchema Challenge 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Yisen Feng, Yuquan Xie, Zaijing Li","submitted_at":"2024-06-22T07:20:39Z","abstract_excerpt":"In this report, we present our champion solution for Ego4D EgoSchema Challenge in CVPR 2024. To deeply integrate the powerful egocentric captioning model and question reasoning model, we propose a novel Hierarchical Comprehension scheme for egocentric video Question Answering, named HCQA. It consists of three stages: Fine-grained Caption Generation, Context-driven Summarization, and Inference-guided Answering. Given a long-form video, HCQA captures local detailed visual information and global summarised visual information via Fine-grained Caption Generation and Context-driven Summarization, re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15771","kind":"arxiv","version":2},"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/2406.15771/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":"2026-07-05T09:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tbs+0XMhvRnoQpx1iWYCC1Iti5mrSnpDg2Hln7txfd0H0S2De9XujAqJxjntqWlUu++h4LYahFlkLPS1rBO6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:20:25.473950Z"},"content_sha256":"7e91e851b379db098b55de1a693589d82f51484aa95727779e433cc944f49601","schema_version":"1.0","event_id":"sha256:7e91e851b379db098b55de1a693589d82f51484aa95727779e433cc944f49601"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BDHQXFVJ6J4C2APDBQYE3RDJNQ/bundle.json","state_url":"https://pith.science/pith/BDHQXFVJ6J4C2APDBQYE3RDJNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BDHQXFVJ6J4C2APDBQYE3RDJNQ/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":"2026-08-15T23:20:25Z","links":{"resolver":"https://pith.science/pith/BDHQXFVJ6J4C2APDBQYE3RDJNQ","bundle":"https://pith.science/pith/BDHQXFVJ6J4C2APDBQYE3RDJNQ/bundle.json","state":"https://pith.science/pith/BDHQXFVJ6J4C2APDBQYE3RDJNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BDHQXFVJ6J4C2APDBQYE3RDJNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BDHQXFVJ6J4C2APDBQYE3RDJNQ","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":"cece7b725d605e2125fd25692f65d21eefd9e098627779ef4a876fce0d8842a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T07:20:39Z","title_canon_sha256":"cc5d3b16a1bb82860451fb805b58cc43cb1d6e94bffea70839437579a86a49e0"},"schema_version":"1.0","source":{"id":"2406.15771","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15771","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15771v2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15771","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"BDHQXFVJ6J4C","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"BDHQXFVJ6J4C2APD","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"BDHQXFVJ","created_at":"2026-07-05T09:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:7e91e851b379db098b55de1a693589d82f51484aa95727779e433cc944f49601","target":"graph","created_at":"2026-07-05T09:27:23Z","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/2406.15771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this report, we present our champion solution for Ego4D EgoSchema Challenge in CVPR 2024. To deeply integrate the powerful egocentric captioning model and question reasoning model, we propose a novel Hierarchical Comprehension scheme for egocentric video Question Answering, named HCQA. It consists of three stages: Fine-grained Caption Generation, Context-driven Summarization, and Inference-guided Answering. Given a long-form video, HCQA captures local detailed visual information and global summarised visual information via Fine-grained Caption Generation and Context-driven Summarization, re","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Yisen Feng, Yuquan Xie, Zaijing Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T07:20:39Z","title":"HCQA @ Ego4D EgoSchema Challenge 2024"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15771","kind":"arxiv","version":2},"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":"sha256:7f83fd8ea83d884f307c2187249fcb0157e2b082b68df69df3b9cc80f0cafebf","target":"record","created_at":"2026-07-05T09:27:23Z","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":"cece7b725d605e2125fd25692f65d21eefd9e098627779ef4a876fce0d8842a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T07:20:39Z","title_canon_sha256":"cc5d3b16a1bb82860451fb805b58cc43cb1d6e94bffea70839437579a86a49e0"},"schema_version":"1.0","source":{"id":"2406.15771","kind":"arxiv","version":2}},"canonical_sha256":"08cf0b96a9f2782d01e30c304dc4696c2d43c4996de311cbf81616b86ed352a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08cf0b96a9f2782d01e30c304dc4696c2d43c4996de311cbf81616b86ed352a7","first_computed_at":"2026-07-05T09:27:23.612995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:23.612995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AXAImiwD6+jHYe+6FDFrl4sJo4o8m+JW+Dz9BwquK7DOGwRnR7M/HmiVW+x3NZ8tZ8EgGnOV1A2epxBVBTR/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:23.613440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15771","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f83fd8ea83d884f307c2187249fcb0157e2b082b68df69df3b9cc80f0cafebf","sha256:7e91e851b379db098b55de1a693589d82f51484aa95727779e433cc944f49601"],"state_sha256":"ca5ae82e86855a7502dddf09e0255fed67d5f56ae73cbb61cd793cdb230f84aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fud+xuqWR1H1gakSwwfOvZkbzbhZr2Wtq0jA4V9/8LSHH74SmcWQAh41fet76TPwAU2j1u5bCZjnlJ77pWvcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:20:25.478441Z","bundle_sha256":"c266f761738f9dffa92f9c2f47bd3d2d61e71df3fbc94b95ad830cbd0e7d44f6"}}