{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SJD275SXA5H37E3O5YNBZJ2S5H","short_pith_number":"pith:SJD275SX","canonical_record":{"source":{"id":"1804.09412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T08:10:35Z","cross_cats_sorted":[],"title_canon_sha256":"fa9d1ad749c03bce63ac969cf7335f6d3af0ee7f3bd17ace14708531d96d49fe","abstract_canon_sha256":"5aefa42bdd2e72ca5c54375d8a6e18a501f076a1943381de3768cf81b32fd874"},"schema_version":"1.0"},"canonical_sha256":"9247aff657074fbf936eee1a1ca752e9cfb76fcf99f01f1d9a1a13deff85c58e","source":{"kind":"arxiv","id":"1804.09412","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09412","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09412v1","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09412","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"SJD275SXA5H3","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SJD275SXA5H37E3O","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SJD275SX","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SJD275SXA5H37E3O5YNBZJ2S5H","target":"record","payload":{"canonical_record":{"source":{"id":"1804.09412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T08:10:35Z","cross_cats_sorted":[],"title_canon_sha256":"fa9d1ad749c03bce63ac969cf7335f6d3af0ee7f3bd17ace14708531d96d49fe","abstract_canon_sha256":"5aefa42bdd2e72ca5c54375d8a6e18a501f076a1943381de3768cf81b32fd874"},"schema_version":"1.0"},"canonical_sha256":"9247aff657074fbf936eee1a1ca752e9cfb76fcf99f01f1d9a1a13deff85c58e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:31.877907Z","signature_b64":"Q4XarTSEQCVRav5okNGxwOiP/7a99lQyprSes9BI8NMiA474YvLgCLDQJd140Yg69NK1701NWn3Ev5bVlezhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9247aff657074fbf936eee1a1ca752e9cfb76fcf99f01f1d9a1a13deff85c58e","last_reissued_at":"2026-05-18T00:17:31.877371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:31.877371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.09412","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":"2026-05-18T00:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ua6p7Eqx8Y6PrvjOaMNC3Jvk5SmoyxgINkdAf0Vv0njXZXKURR/vtCVGEnlwFU1CtH63c0AZVmFghWL6HyeZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:14:47.215476Z"},"content_sha256":"1428c9df4c8f20e7214cce7cc56acd26ad8e28495c2936f313d6b4faf00546d6","schema_version":"1.0","event_id":"sha256:1428c9df4c8f20e7214cce7cc56acd26ad8e28495c2936f313d6b4faf00546d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SJD275SXA5H37E3O5YNBZJ2S5H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Movie Question Answering: Remembering the Textual Cues for Layered Visual Contents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Richang Hong, Yahong Han, Youjiang Xu","submitted_at":"2018-04-25T08:10:35Z","abstract_excerpt":"Movies provide us with a mass of visual content as well as attracting stories. Existing methods have illustrated that understanding movie stories through only visual content is still a hard problem. In this paper, for answering questions about movies, we put forward a Layered Memory Network (LMN) that represents frame-level and clip-level movie content by the Static Word Memory module and the Dynamic Subtitle Memory module, respectively. Particularly, we firstly extract words and sentences from the training movie subtitles. Then the hierarchically formed movie representations, which are learne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09412","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":"2026-05-18T00:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nRwEcrcm795SnJ4//T0mQmtdBSZ6jJz00NTn78A3AYT80ijujAQo9GZkxanS5S/ZcTuCCZhn1iANeCs6GobODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:14:47.216087Z"},"content_sha256":"a84fde863a707f6f1bd96e093fd944ed9d88bd930bfafafea74af3db40bfcdc0","schema_version":"1.0","event_id":"sha256:a84fde863a707f6f1bd96e093fd944ed9d88bd930bfafafea74af3db40bfcdc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJD275SXA5H37E3O5YNBZJ2S5H/bundle.json","state_url":"https://pith.science/pith/SJD275SXA5H37E3O5YNBZJ2S5H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJD275SXA5H37E3O5YNBZJ2S5H/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":"2026-06-06T20:14:47Z","links":{"resolver":"https://pith.science/pith/SJD275SXA5H37E3O5YNBZJ2S5H","bundle":"https://pith.science/pith/SJD275SXA5H37E3O5YNBZJ2S5H/bundle.json","state":"https://pith.science/pith/SJD275SXA5H37E3O5YNBZJ2S5H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJD275SXA5H37E3O5YNBZJ2S5H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SJD275SXA5H37E3O5YNBZJ2S5H","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":"5aefa42bdd2e72ca5c54375d8a6e18a501f076a1943381de3768cf81b32fd874","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T08:10:35Z","title_canon_sha256":"fa9d1ad749c03bce63ac969cf7335f6d3af0ee7f3bd17ace14708531d96d49fe"},"schema_version":"1.0","source":{"id":"1804.09412","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09412","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09412v1","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09412","created_at":"2026-05-18T00:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"SJD275SXA5H3","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SJD275SXA5H37E3O","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SJD275SX","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:a84fde863a707f6f1bd96e093fd944ed9d88bd930bfafafea74af3db40bfcdc0","target":"graph","created_at":"2026-05-18T00:17:31Z","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":"Movies provide us with a mass of visual content as well as attracting stories. Existing methods have illustrated that understanding movie stories through only visual content is still a hard problem. In this paper, for answering questions about movies, we put forward a Layered Memory Network (LMN) that represents frame-level and clip-level movie content by the Static Word Memory module and the Dynamic Subtitle Memory module, respectively. Particularly, we firstly extract words and sentences from the training movie subtitles. Then the hierarchically formed movie representations, which are learne","authors_text":"Bo Wang, Richang Hong, Yahong Han, Youjiang Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T08:10:35Z","title":"Movie Question Answering: Remembering the Textual Cues for Layered Visual Contents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09412","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":"sha256:1428c9df4c8f20e7214cce7cc56acd26ad8e28495c2936f313d6b4faf00546d6","target":"record","created_at":"2026-05-18T00:17:31Z","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":"5aefa42bdd2e72ca5c54375d8a6e18a501f076a1943381de3768cf81b32fd874","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T08:10:35Z","title_canon_sha256":"fa9d1ad749c03bce63ac969cf7335f6d3af0ee7f3bd17ace14708531d96d49fe"},"schema_version":"1.0","source":{"id":"1804.09412","kind":"arxiv","version":1}},"canonical_sha256":"9247aff657074fbf936eee1a1ca752e9cfb76fcf99f01f1d9a1a13deff85c58e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9247aff657074fbf936eee1a1ca752e9cfb76fcf99f01f1d9a1a13deff85c58e","first_computed_at":"2026-05-18T00:17:31.877371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:31.877371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q4XarTSEQCVRav5okNGxwOiP/7a99lQyprSes9BI8NMiA474YvLgCLDQJd140Yg69NK1701NWn3Ev5bVlezhDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:31.877907Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.09412","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1428c9df4c8f20e7214cce7cc56acd26ad8e28495c2936f313d6b4faf00546d6","sha256:a84fde863a707f6f1bd96e093fd944ed9d88bd930bfafafea74af3db40bfcdc0"],"state_sha256":"004bdfcb1ec3a080bc3ba1d5e225e75f396419e006a575080820b3850fb55cbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oiNeHI9E3buHO4rVBsucxbgDjLTQUJuTOjFDI87NnVBrKvWvO6kWCyfnubieYZR6A1MyjoQ0hk6RxOl3OxaqDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T20:14:47.219359Z","bundle_sha256":"37a7f54c0c65da5a46dba3f2e56c9020a7a503fe16229fe0888bcd3c7ce307d9"}}