{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BS54NV5H5HJHR72AIUC6OV4NYW","short_pith_number":"pith:BS54NV5H","canonical_record":{"source":{"id":"1705.01253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T04:46:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"de464f5c0f665d3ab23a3825cbd858d1afa4fab923dfdd67d9eb69b8f0bfec66","abstract_canon_sha256":"a2197ffeb82f3a3b28bfb3236e1ff9b26787dac157e07fcdd5b779328ea7d7bd"},"schema_version":"1.0"},"canonical_sha256":"0cbbc6d7a7e9d278ff404505e7578dc5b7d8f3f2cbaa20d597f9427f8a002ff5","source":{"kind":"arxiv","id":"1705.01253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01253","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01253v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01253","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"BS54NV5H5HJH","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BS54NV5H5HJHR72A","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BS54NV5H","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BS54NV5H5HJHR72AIUC6OV4NYW","target":"record","payload":{"canonical_record":{"source":{"id":"1705.01253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T04:46:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"de464f5c0f665d3ab23a3825cbd858d1afa4fab923dfdd67d9eb69b8f0bfec66","abstract_canon_sha256":"a2197ffeb82f3a3b28bfb3236e1ff9b26787dac157e07fcdd5b779328ea7d7bd"},"schema_version":"1.0"},"canonical_sha256":"0cbbc6d7a7e9d278ff404505e7578dc5b7d8f3f2cbaa20d597f9427f8a002ff5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:05.562030Z","signature_b64":"ZfkXaRWa3GC5sY/g3XYtik9aFa/nkeneO9Rd3X/OiUAFoWInFPwK9NuSsLxH6t6IL9plDOgIvUvbzbW24TPgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cbbc6d7a7e9d278ff404505e7578dc5b7d8f3f2cbaa20d597f9427f8a002ff5","last_reissued_at":"2026-05-18T00:45:05.561558Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:05.561558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.01253","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjFc3rsttUntgdKADtQO6gPhR8zg/mnvI55no0TtyvNAsMP+m742mF9F1snVpKqgC/QiaGhF+Uo+QuOBFoqIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:13:26.597350Z"},"content_sha256":"1020cad4fa4ef49176a3fed326a9a3c3bf960def78b6884258ec54f67af12eef","schema_version":"1.0","event_id":"sha256:1020cad4fa4ef49176a3fed326a9a3c3bf960def78b6884258ec54f67af12eef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BS54NV5H5HJHR72AIUC6OV4NYW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Forgettable-Watcher Model for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Deng Cai, Hongyang Xue, Zhou Zhao","submitted_at":"2017-05-03T04:46:33Z","abstract_excerpt":"A number of visual question answering approaches have been proposed recently, aiming at understanding the visual scenes by answering the natural language questions. While the image question answering has drawn significant attention, video question answering is largely unexplored.\n  Video-QA is different from Image-QA since the information and the events are scattered among multiple frames. In order to better utilize the temporal structure of the videos and the phrasal structures of the answers, we propose two mechanisms: the re-watching and the re-reading mechanisms and combine them into the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01253","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFBVje8nPMT+bAFewBidGO5yEgxiC72KEVCdQ3yER5mHfoKWTrLBTKW29IHIackdpjsnUKL+aBM1DrT1f3JfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:13:26.597709Z"},"content_sha256":"fcb0edf2f99812093d492fea60fd0636bacffa8c18f6ad786cd6be97596ff798","schema_version":"1.0","event_id":"sha256:fcb0edf2f99812093d492fea60fd0636bacffa8c18f6ad786cd6be97596ff798"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BS54NV5H5HJHR72AIUC6OV4NYW/bundle.json","state_url":"https://pith.science/pith/BS54NV5H5HJHR72AIUC6OV4NYW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BS54NV5H5HJHR72AIUC6OV4NYW/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":"2026-05-30T12:13:26Z","links":{"resolver":"https://pith.science/pith/BS54NV5H5HJHR72AIUC6OV4NYW","bundle":"https://pith.science/pith/BS54NV5H5HJHR72AIUC6OV4NYW/bundle.json","state":"https://pith.science/pith/BS54NV5H5HJHR72AIUC6OV4NYW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BS54NV5H5HJHR72AIUC6OV4NYW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BS54NV5H5HJHR72AIUC6OV4NYW","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":"a2197ffeb82f3a3b28bfb3236e1ff9b26787dac157e07fcdd5b779328ea7d7bd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T04:46:33Z","title_canon_sha256":"de464f5c0f665d3ab23a3825cbd858d1afa4fab923dfdd67d9eb69b8f0bfec66"},"schema_version":"1.0","source":{"id":"1705.01253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01253","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01253v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01253","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"BS54NV5H5HJH","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BS54NV5H5HJHR72A","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BS54NV5H","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:fcb0edf2f99812093d492fea60fd0636bacffa8c18f6ad786cd6be97596ff798","target":"graph","created_at":"2026-05-18T00:45:05Z","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":"A number of visual question answering approaches have been proposed recently, aiming at understanding the visual scenes by answering the natural language questions. While the image question answering has drawn significant attention, video question answering is largely unexplored.\n  Video-QA is different from Image-QA since the information and the events are scattered among multiple frames. In order to better utilize the temporal structure of the videos and the phrasal structures of the answers, we propose two mechanisms: the re-watching and the re-reading mechanisms and combine them into the f","authors_text":"Deng Cai, Hongyang Xue, Zhou Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T04:46:33Z","title":"The Forgettable-Watcher Model for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01253","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":"sha256:1020cad4fa4ef49176a3fed326a9a3c3bf960def78b6884258ec54f67af12eef","target":"record","created_at":"2026-05-18T00:45:05Z","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":"a2197ffeb82f3a3b28bfb3236e1ff9b26787dac157e07fcdd5b779328ea7d7bd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T04:46:33Z","title_canon_sha256":"de464f5c0f665d3ab23a3825cbd858d1afa4fab923dfdd67d9eb69b8f0bfec66"},"schema_version":"1.0","source":{"id":"1705.01253","kind":"arxiv","version":1}},"canonical_sha256":"0cbbc6d7a7e9d278ff404505e7578dc5b7d8f3f2cbaa20d597f9427f8a002ff5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cbbc6d7a7e9d278ff404505e7578dc5b7d8f3f2cbaa20d597f9427f8a002ff5","first_computed_at":"2026-05-18T00:45:05.561558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:05.561558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZfkXaRWa3GC5sY/g3XYtik9aFa/nkeneO9Rd3X/OiUAFoWInFPwK9NuSsLxH6t6IL9plDOgIvUvbzbW24TPgBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:05.562030Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.01253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1020cad4fa4ef49176a3fed326a9a3c3bf960def78b6884258ec54f67af12eef","sha256:fcb0edf2f99812093d492fea60fd0636bacffa8c18f6ad786cd6be97596ff798"],"state_sha256":"4badefa72f5cd8c88fcb5f15aa61fb27757fe31fd2aa875eaf8fec49eb25cf22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a1Hm0hcpEBeJdrcXRDL6bodGAE9uxjgajFdmsMK2KAc7IA5ngK5mNNzXParE+MEbfG4gsn2U0lI5wHb66mYXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:13:26.599713Z","bundle_sha256":"23159042c4258c6077132fe427beaded262de7768ce9a1cd4380f22094840c93"}}