{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2KCRIT4B52WY52BAPQ7X7HOCMU","short_pith_number":"pith:2KCRIT4B","canonical_record":{"source":{"id":"1803.10906","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-29T02:47:49Z","cross_cats_sorted":[],"title_canon_sha256":"1d8188e4b4e2e4c01f1153423616a038ba9afdc5c3ad11a9089994fcab6ace33","abstract_canon_sha256":"e5213adc8b905d185086a95c95c5df395dfded2b81eaead70280153a9f7a06bf"},"schema_version":"1.0"},"canonical_sha256":"d285144f81eead8ee8207c3f7f9dc2652d640c9b0961e38e10e31b54ec72aff2","source":{"kind":"arxiv","id":"1803.10906","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10906","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10906v1","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10906","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"2KCRIT4B52WY","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2KCRIT4B52WY52BA","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2KCRIT4B","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2KCRIT4B52WY52BAPQ7X7HOCMU","target":"record","payload":{"canonical_record":{"source":{"id":"1803.10906","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-29T02:47:49Z","cross_cats_sorted":[],"title_canon_sha256":"1d8188e4b4e2e4c01f1153423616a038ba9afdc5c3ad11a9089994fcab6ace33","abstract_canon_sha256":"e5213adc8b905d185086a95c95c5df395dfded2b81eaead70280153a9f7a06bf"},"schema_version":"1.0"},"canonical_sha256":"d285144f81eead8ee8207c3f7f9dc2652d640c9b0961e38e10e31b54ec72aff2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:49.835571Z","signature_b64":"fZCef4QKXTOW88CimWWbLQ9U342SEbecfr/47SkOtzX7sP6E06+j6uR4TJYH6CUzYvBHEgwBJGTog2dOfErqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d285144f81eead8ee8207c3f7f9dc2652d640c9b0961e38e10e31b54ec72aff2","last_reissued_at":"2026-05-18T00:19:49.834955Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:49.834955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.10906","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":"2026-05-18T00:19:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JpybstfYiRr4Rnn4eCPYYe/IBLlC4Osk/kVtcmVwLcOfMVD9PD9/tz1datGP/JoOmU7x4Ju0kH5s+MSGugAhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T10:31:33.245672Z"},"content_sha256":"1c8ff29263ac7fb7b5001aa1ae53e51b34b6fd33825b40486af21b0ebe8883fd","schema_version":"1.0","event_id":"sha256:1c8ff29263ac7fb7b5001aa1ae53e51b34b6fd33825b40486af21b0ebe8883fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2KCRIT4B52WY52BAPQ7X7HOCMU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Motion-Appearance Co-Memory Networks for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiyang Gao, Kan Chen, Ram Nevatia, Runzhou Ge","submitted_at":"2018-03-29T02:47:49Z","abstract_excerpt":"Video Question Answering (QA) is an important task in understanding video temporal structure. We observe that there are three unique attributes of video QA compared with image QA: (1) it deals with long sequences of images containing richer information not only in quantity but also in variety; (2) motion and appearance information are usually correlated with each other and able to provide useful attention cues to the other; (3) different questions require different number of frames to infer the answer. Based these observations, we propose a motion-appearance comemory network for video QA. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10906","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":""},"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":"2026-05-18T00:19:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYLiBBeVs4EzwTqVQDNxhal9viiR5DcEHm7apWcu2JMraVRIfn3mZhmiHNtrEmrn2mO8fKOceK0Bq2bfLJk7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T10:31:33.246023Z"},"content_sha256":"bb3578b5a36a6e37158fbfae08f58ca6bd9bc2b1a3b8bf7c1fb533a5518d640b","schema_version":"1.0","event_id":"sha256:bb3578b5a36a6e37158fbfae08f58ca6bd9bc2b1a3b8bf7c1fb533a5518d640b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/bundle.json","state_url":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/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":"2026-06-25T10:31:33Z","links":{"resolver":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU","bundle":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/bundle.json","state":"https://pith.science/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KCRIT4B52WY52BAPQ7X7HOCMU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2KCRIT4B52WY52BAPQ7X7HOCMU","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":"e5213adc8b905d185086a95c95c5df395dfded2b81eaead70280153a9f7a06bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-29T02:47:49Z","title_canon_sha256":"1d8188e4b4e2e4c01f1153423616a038ba9afdc5c3ad11a9089994fcab6ace33"},"schema_version":"1.0","source":{"id":"1803.10906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10906","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10906v1","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10906","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"2KCRIT4B52WY","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2KCRIT4B52WY52BA","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2KCRIT4B","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:bb3578b5a36a6e37158fbfae08f58ca6bd9bc2b1a3b8bf7c1fb533a5518d640b","target":"graph","created_at":"2026-05-18T00:19:49Z","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"},"paper":{"abstract_excerpt":"Video Question Answering (QA) is an important task in understanding video temporal structure. We observe that there are three unique attributes of video QA compared with image QA: (1) it deals with long sequences of images containing richer information not only in quantity but also in variety; (2) motion and appearance information are usually correlated with each other and able to provide useful attention cues to the other; (3) different questions require different number of frames to infer the answer. Based these observations, we propose a motion-appearance comemory network for video QA. Our ","authors_text":"Jiyang Gao, Kan Chen, Ram Nevatia, Runzhou Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-29T02:47:49Z","title":"Motion-Appearance Co-Memory Networks for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10906","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":"sha256:1c8ff29263ac7fb7b5001aa1ae53e51b34b6fd33825b40486af21b0ebe8883fd","target":"record","created_at":"2026-05-18T00:19:49Z","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":"e5213adc8b905d185086a95c95c5df395dfded2b81eaead70280153a9f7a06bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-29T02:47:49Z","title_canon_sha256":"1d8188e4b4e2e4c01f1153423616a038ba9afdc5c3ad11a9089994fcab6ace33"},"schema_version":"1.0","source":{"id":"1803.10906","kind":"arxiv","version":1}},"canonical_sha256":"d285144f81eead8ee8207c3f7f9dc2652d640c9b0961e38e10e31b54ec72aff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d285144f81eead8ee8207c3f7f9dc2652d640c9b0961e38e10e31b54ec72aff2","first_computed_at":"2026-05-18T00:19:49.834955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:49.834955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fZCef4QKXTOW88CimWWbLQ9U342SEbecfr/47SkOtzX7sP6E06+j6uR4TJYH6CUzYvBHEgwBJGTog2dOfErqDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:49.835571Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.10906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c8ff29263ac7fb7b5001aa1ae53e51b34b6fd33825b40486af21b0ebe8883fd","sha256:bb3578b5a36a6e37158fbfae08f58ca6bd9bc2b1a3b8bf7c1fb533a5518d640b"],"state_sha256":"e7629c03938750e4a41046e38a967f9a64c98971492d261b8d1cba2ffca78181"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aNrMDduUiv0d4YVRA1MZP/goTg79/NVGWxz00Kr2cyUa3kXJaztcTBQYmuMfnRRvw8NXB8ULIMos097k9vySBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T10:31:33.247954Z","bundle_sha256":"2bcb73c5ed3b27236dbd3e6c93cbd82a95e5d15f1b491d3ca145a0eb10243bf3"}}