{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RONZAWYJ2NUBK466E2MA3F4SPL","short_pith_number":"pith:RONZAWYJ","canonical_record":{"source":{"id":"2106.13432","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T05:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"1f6df6d8cc285c8418c72cf2824429998e90a8ed3da23e14e9be0f45b535e80c","abstract_canon_sha256":"adfa02ca6fd3b7167afc9e7b34e2151713df5ea8ac2eab84779948b7e19470e3"},"schema_version":"1.0"},"canonical_sha256":"8b9b905b09d3681573de26980d97927ae88f44627d629691e97f1355df15c0dc","source":{"kind":"arxiv","id":"2106.13432","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13432","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13432v2","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13432","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"pith_short_12","alias_value":"RONZAWYJ2NUB","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"pith_short_16","alias_value":"RONZAWYJ2NUBK466","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"pith_short_8","alias_value":"RONZAWYJ","created_at":"2026-07-05T03:08:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RONZAWYJ2NUBK466E2MA3F4SPL","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13432","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T05:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"1f6df6d8cc285c8418c72cf2824429998e90a8ed3da23e14e9be0f45b535e80c","abstract_canon_sha256":"adfa02ca6fd3b7167afc9e7b34e2151713df5ea8ac2eab84779948b7e19470e3"},"schema_version":"1.0"},"canonical_sha256":"8b9b905b09d3681573de26980d97927ae88f44627d629691e97f1355df15c0dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:46.409411Z","signature_b64":"GsAEXigJ3tEswv2EFIIZaQ8HP5VDM0HnZu+2m49O3j5QCCdHiuteNETS/43Q2gpZVgoVqXx/QNN+xft3f593BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b9b905b09d3681573de26980d97927ae88f44627d629691e97f1355df15c0dc","last_reissued_at":"2026-07-05T03:08:46.408897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:46.408897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13432","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":"2026-07-05T03:08:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xJufvPw3INYfNG85qyl9DLStybWD8WgjyExCuUDGq/wr23cdKHCpoRwGUWB17ayYEtRqnNKuvMBiRgwN297Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:17:58.442319Z"},"content_sha256":"69afd54968bce8c67bb966a3a01c7cebb3efdcdbe0cd9efb87cdaed0b46ada10","schema_version":"1.0","event_id":"sha256:69afd54968bce8c67bb966a3a01c7cebb3efdcdbe0cd9efb87cdaed0b46ada10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RONZAWYJ2NUBK466E2MA3F4SPL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Hoang Dang, Thao Minh Le, Truyen Tran, Vuong Le","submitted_at":"2021-06-25T05:12:42Z","abstract_excerpt":"Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time. High-level reasoning demands lifting from associative visual pattern recognition to symbol-like manipulation over objects, their behavior and interactions. Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects. At each stage of the video event flow, these objects interact with each othe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13432","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/2106.13432/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":"2026-07-05T03:08:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n0kximdw1vA0d9NOhbW/FYJkmqswxlg03DbGZJOGlehDt8tuZR1rx8TpFozZC0bIQvPNdfHBAjQg4GXgNYLxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:17:58.443219Z"},"content_sha256":"3df7efead154acc92fe1888f51df61a88824f9b618d4699562a7132b5c3b67e9","schema_version":"1.0","event_id":"sha256:3df7efead154acc92fe1888f51df61a88824f9b618d4699562a7132b5c3b67e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/bundle.json","state_url":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RONZAWYJ2NUBK466E2MA3F4SPL/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":"2026-08-07T13:17:58Z","links":{"resolver":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL","bundle":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/bundle.json","state":"https://pith.science/pith/RONZAWYJ2NUBK466E2MA3F4SPL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RONZAWYJ2NUBK466E2MA3F4SPL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RONZAWYJ2NUBK466E2MA3F4SPL","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":"adfa02ca6fd3b7167afc9e7b34e2151713df5ea8ac2eab84779948b7e19470e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T05:12:42Z","title_canon_sha256":"1f6df6d8cc285c8418c72cf2824429998e90a8ed3da23e14e9be0f45b535e80c"},"schema_version":"1.0","source":{"id":"2106.13432","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13432","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13432v2","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13432","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"pith_short_12","alias_value":"RONZAWYJ2NUB","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"pith_short_16","alias_value":"RONZAWYJ2NUBK466","created_at":"2026-07-05T03:08:46Z"},{"alias_kind":"pith_short_8","alias_value":"RONZAWYJ","created_at":"2026-07-05T03:08:46Z"}],"graph_snapshots":[{"event_id":"sha256:3df7efead154acc92fe1888f51df61a88824f9b618d4699562a7132b5c3b67e9","target":"graph","created_at":"2026-07-05T03:08:46Z","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/2106.13432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time. High-level reasoning demands lifting from associative visual pattern recognition to symbol-like manipulation over objects, their behavior and interactions. Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects. At each stage of the video event flow, these objects interact with each othe","authors_text":"Long Hoang Dang, Thao Minh Le, Truyen Tran, Vuong Le","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T05:12:42Z","title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13432","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":"sha256:69afd54968bce8c67bb966a3a01c7cebb3efdcdbe0cd9efb87cdaed0b46ada10","target":"record","created_at":"2026-07-05T03:08:46Z","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":"adfa02ca6fd3b7167afc9e7b34e2151713df5ea8ac2eab84779948b7e19470e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T05:12:42Z","title_canon_sha256":"1f6df6d8cc285c8418c72cf2824429998e90a8ed3da23e14e9be0f45b535e80c"},"schema_version":"1.0","source":{"id":"2106.13432","kind":"arxiv","version":2}},"canonical_sha256":"8b9b905b09d3681573de26980d97927ae88f44627d629691e97f1355df15c0dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b9b905b09d3681573de26980d97927ae88f44627d629691e97f1355df15c0dc","first_computed_at":"2026-07-05T03:08:46.408897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:08:46.408897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GsAEXigJ3tEswv2EFIIZaQ8HP5VDM0HnZu+2m49O3j5QCCdHiuteNETS/43Q2gpZVgoVqXx/QNN+xft3f593BA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:08:46.409411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13432","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69afd54968bce8c67bb966a3a01c7cebb3efdcdbe0cd9efb87cdaed0b46ada10","sha256:3df7efead154acc92fe1888f51df61a88824f9b618d4699562a7132b5c3b67e9"],"state_sha256":"3e3414432dc0c54921257630387a663dfb9d1cba84aca09de5e5b06b298badc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8Kr4XMEw3n2tt6gtDPj2anwzW0hzHm7MO2CezNJizN/wFeFuyIXU9SAnZJycfwMijBE3UR5IH4ZmV3Q2IQkBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T13:17:58.476122Z","bundle_sha256":"58a101142d23b472362dc9b4c1b69b981599ec9eaaad67f7ab7cc533c0103524"}}