{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HJRWVYFP3K4RC45SP43QVS43XB","short_pith_number":"pith:HJRWVYFP","canonical_record":{"source":{"id":"1812.06587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-17T02:46:17Z","cross_cats_sorted":[],"title_canon_sha256":"c91e37af90bb791081bff0392f0dec634432d78f57f94f45b9d1f5a9b9f43eb4","abstract_canon_sha256":"5bad264ffbeaa9719c2369b45df385934697d86c3597de72997beb19790f838e"},"schema_version":"1.0"},"canonical_sha256":"3a636ae0afdab91173b27f370acb9bb8702ca88b3d69665b738ef9256be912d0","source":{"kind":"arxiv","id":"1812.06587","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06587","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06587v2","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06587","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"HJRWVYFP3K4R","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HJRWVYFP3K4RC45S","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HJRWVYFP","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HJRWVYFP3K4RC45SP43QVS43XB","target":"record","payload":{"canonical_record":{"source":{"id":"1812.06587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-17T02:46:17Z","cross_cats_sorted":[],"title_canon_sha256":"c91e37af90bb791081bff0392f0dec634432d78f57f94f45b9d1f5a9b9f43eb4","abstract_canon_sha256":"5bad264ffbeaa9719c2369b45df385934697d86c3597de72997beb19790f838e"},"schema_version":"1.0"},"canonical_sha256":"3a636ae0afdab91173b27f370acb9bb8702ca88b3d69665b738ef9256be912d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:02.258756Z","signature_b64":"TJY1K2KECMMi6qAEDIzpDoACPLvrGiNPi2zyuPx7UFmMImwVKaMfJeWVS7wfbhrlnnuX8R1QtBD0qRHXvew9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a636ae0afdab91173b27f370acb9bb8702ca88b3d69665b738ef9256be912d0","last_reissued_at":"2026-05-17T23:47:02.258243Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:02.258243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.06587","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":"2026-05-17T23:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6LGnUiMKf7xwxS265I/83639T/fA2UH+yxgbycW7H+x6GzJHhUBcydpWoKAix/ruvzGKst4X122CbzSpFrkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T13:27:51.963121Z"},"content_sha256":"6466143763d44ac8822b4e98487c3498b2a6b1508913cb96e754a7f347069284","schema_version":"1.0","event_id":"sha256:6466143763d44ac8822b4e98487c3498b2a6b1508913cb96e754a7f347069284"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HJRWVYFP3K4RC45SP43QVS43XB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounded Video Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason J. Corso, Luowei Zhou, Marcus Rohrbach, Xinlei Chen, Yannis Kalantidis","submitted_at":"2018-12-17T02:46:17Z","abstract_excerpt":"Video description is one of the most challenging problems in vision and language understanding due to the large variability both on the video and language side. Models, hence, typically shortcut the difficulty in recognition and generate plausible sentences that are based on priors but are not necessarily grounded in the video. In this work, we explicitly link the sentence to the evidence in the video by annotating each noun phrase in a sentence with the corresponding bounding box in one of the frames of a video. Our dataset, ActivityNet-Entities, augments the challenging ActivityNet Captions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06587","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":""},"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":"2026-05-17T23:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ph03G/eZClRr/Spy3f22oDrx6w7PTDDNnXlx4bt82XfAiz90QDhVYQJZXkIw/YTAeIP8Lc2fMGGxluhvh3oYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T13:27:51.963494Z"},"content_sha256":"fd74dfc3084eb652e1eb330e4d0240ba14661bcc45da44343a1a19172d369be3","schema_version":"1.0","event_id":"sha256:fd74dfc3084eb652e1eb330e4d0240ba14661bcc45da44343a1a19172d369be3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJRWVYFP3K4RC45SP43QVS43XB/bundle.json","state_url":"https://pith.science/pith/HJRWVYFP3K4RC45SP43QVS43XB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJRWVYFP3K4RC45SP43QVS43XB/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":"2026-05-19T13:27:51Z","links":{"resolver":"https://pith.science/pith/HJRWVYFP3K4RC45SP43QVS43XB","bundle":"https://pith.science/pith/HJRWVYFP3K4RC45SP43QVS43XB/bundle.json","state":"https://pith.science/pith/HJRWVYFP3K4RC45SP43QVS43XB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJRWVYFP3K4RC45SP43QVS43XB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HJRWVYFP3K4RC45SP43QVS43XB","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":"5bad264ffbeaa9719c2369b45df385934697d86c3597de72997beb19790f838e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-17T02:46:17Z","title_canon_sha256":"c91e37af90bb791081bff0392f0dec634432d78f57f94f45b9d1f5a9b9f43eb4"},"schema_version":"1.0","source":{"id":"1812.06587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06587","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06587v2","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06587","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"HJRWVYFP3K4R","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HJRWVYFP3K4RC45S","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HJRWVYFP","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:fd74dfc3084eb652e1eb330e4d0240ba14661bcc45da44343a1a19172d369be3","target":"graph","created_at":"2026-05-17T23:47:02Z","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 description is one of the most challenging problems in vision and language understanding due to the large variability both on the video and language side. Models, hence, typically shortcut the difficulty in recognition and generate plausible sentences that are based on priors but are not necessarily grounded in the video. In this work, we explicitly link the sentence to the evidence in the video by annotating each noun phrase in a sentence with the corresponding bounding box in one of the frames of a video. Our dataset, ActivityNet-Entities, augments the challenging ActivityNet Captions ","authors_text":"Jason J. Corso, Luowei Zhou, Marcus Rohrbach, Xinlei Chen, Yannis Kalantidis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-17T02:46:17Z","title":"Grounded Video Description"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06587","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":"sha256:6466143763d44ac8822b4e98487c3498b2a6b1508913cb96e754a7f347069284","target":"record","created_at":"2026-05-17T23:47:02Z","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":"5bad264ffbeaa9719c2369b45df385934697d86c3597de72997beb19790f838e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-17T02:46:17Z","title_canon_sha256":"c91e37af90bb791081bff0392f0dec634432d78f57f94f45b9d1f5a9b9f43eb4"},"schema_version":"1.0","source":{"id":"1812.06587","kind":"arxiv","version":2}},"canonical_sha256":"3a636ae0afdab91173b27f370acb9bb8702ca88b3d69665b738ef9256be912d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a636ae0afdab91173b27f370acb9bb8702ca88b3d69665b738ef9256be912d0","first_computed_at":"2026-05-17T23:47:02.258243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:02.258243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TJY1K2KECMMi6qAEDIzpDoACPLvrGiNPi2zyuPx7UFmMImwVKaMfJeWVS7wfbhrlnnuX8R1QtBD0qRHXvew9DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:02.258756Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.06587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6466143763d44ac8822b4e98487c3498b2a6b1508913cb96e754a7f347069284","sha256:fd74dfc3084eb652e1eb330e4d0240ba14661bcc45da44343a1a19172d369be3"],"state_sha256":"8b75f99c9aa48e3d00a6687a8cf3728c61579f04c21d7cd3310d42375e4dac0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKx8fkV86rzQNTlbi1m/YrqJaL3deT4jZ9aQrp+6+2o+QLhFA3lDYQxrM50S96q+2X2kaW8y7cmCiSu6UpppDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T13:27:51.965243Z","bundle_sha256":"c92af006fb079d42cfd9032525f2b922ecdbcd3c641eae18834fbbe5639747f5"}}