{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4MF5Y2OSJGGBCBU4XQUHOE4UVB","short_pith_number":"pith:4MF5Y2OS","canonical_record":{"source":{"id":"1804.08274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-23T08:18:35Z","cross_cats_sorted":[],"title_canon_sha256":"482c9edeb909115929071b15628b68565e19f6d5337d37c4474798de12fae0a0","abstract_canon_sha256":"712bf6df9d311bafb4529f55b8704cfe040b2b9cdf5748b0f57eff3226428e61"},"schema_version":"1.0"},"canonical_sha256":"e30bdc69d2498c11069cbc28771394a84ed9d6ae62d0c37f4d085ca0a650d17d","source":{"kind":"arxiv","id":"1804.08274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08274","created_at":"2026-05-18T00:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08274v1","created_at":"2026-05-18T00:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08274","created_at":"2026-05-18T00:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"4MF5Y2OSJGGB","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4MF5Y2OSJGGBCBU4","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4MF5Y2OS","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4MF5Y2OSJGGBCBU4XQUHOE4UVB","target":"record","payload":{"canonical_record":{"source":{"id":"1804.08274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-23T08:18:35Z","cross_cats_sorted":[],"title_canon_sha256":"482c9edeb909115929071b15628b68565e19f6d5337d37c4474798de12fae0a0","abstract_canon_sha256":"712bf6df9d311bafb4529f55b8704cfe040b2b9cdf5748b0f57eff3226428e61"},"schema_version":"1.0"},"canonical_sha256":"e30bdc69d2498c11069cbc28771394a84ed9d6ae62d0c37f4d085ca0a650d17d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:48.980380Z","signature_b64":"QaecMKlX2lZhSC+aoqZQFrsClYFpA+VDPfv886lLYs/f5ybTO2D5oFIjAll4JdHhlHReuIT7LdxcoQr5xFEcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e30bdc69d2498c11069cbc28771394a84ed9d6ae62d0c37f4d085ca0a650d17d","last_reissued_at":"2026-05-18T00:17:48.979880Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:48.979880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.08274","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":"2026-05-18T00:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"koU+82Znjt86iW8J4UUeQsIGz1d87ZZFHbwV3GxHYh8fMsIaPxddVDqIcAQbCxb47tZvKmakU65vwweopBTfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:21:43.344029Z"},"content_sha256":"f2f7645c06d15a0a91ac53228a371f416cffddc424818f9ece8391d81b8376cc","schema_version":"1.0","event_id":"sha256:f2f7645c06d15a0a91ac53228a371f416cffddc424818f9ece8391d81b8376cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4MF5Y2OSJGGBCBU4XQUHOE4UVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jointly Localizing and Describing Events for Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyang Chao, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2018-04-23T08:18:35Z","abstract_excerpt":"Automatically describing a video with natural language is regarded as a fundamental challenge in computer vision. The problem nevertheless is not trivial especially when a video contains multiple events to be worthy of mention, which often happens in real videos. A valid question is how to temporally localize and then describe events, which is known as \"dense video captioning.\" In this paper, we present a novel framework for dense video captioning that unifies the localization of temporal event proposals and sentence generation of each proposal, by jointly training them in an end-to-end manner"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08274","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":"2026-05-18T00:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S4Q5rcbfLdJqGZBvyD6SOEb86ktBmti2mlQ78ZX5QajBahZVG2hH3hyeqBvan3Bfdpq17pAFhvxPpz6IIYvVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:21:43.344698Z"},"content_sha256":"32c5b6fbc4cbdb0c4217db13fe6ebdc95f69e7c0a0567c9b7284c1486a777330","schema_version":"1.0","event_id":"sha256:32c5b6fbc4cbdb0c4217db13fe6ebdc95f69e7c0a0567c9b7284c1486a777330"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4MF5Y2OSJGGBCBU4XQUHOE4UVB/bundle.json","state_url":"https://pith.science/pith/4MF5Y2OSJGGBCBU4XQUHOE4UVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4MF5Y2OSJGGBCBU4XQUHOE4UVB/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":"2026-05-25T22:21:43Z","links":{"resolver":"https://pith.science/pith/4MF5Y2OSJGGBCBU4XQUHOE4UVB","bundle":"https://pith.science/pith/4MF5Y2OSJGGBCBU4XQUHOE4UVB/bundle.json","state":"https://pith.science/pith/4MF5Y2OSJGGBCBU4XQUHOE4UVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4MF5Y2OSJGGBCBU4XQUHOE4UVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4MF5Y2OSJGGBCBU4XQUHOE4UVB","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":"712bf6df9d311bafb4529f55b8704cfe040b2b9cdf5748b0f57eff3226428e61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-23T08:18:35Z","title_canon_sha256":"482c9edeb909115929071b15628b68565e19f6d5337d37c4474798de12fae0a0"},"schema_version":"1.0","source":{"id":"1804.08274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08274","created_at":"2026-05-18T00:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08274v1","created_at":"2026-05-18T00:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08274","created_at":"2026-05-18T00:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"4MF5Y2OSJGGB","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4MF5Y2OSJGGBCBU4","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4MF5Y2OS","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:32c5b6fbc4cbdb0c4217db13fe6ebdc95f69e7c0a0567c9b7284c1486a777330","target":"graph","created_at":"2026-05-18T00:17:48Z","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":"Automatically describing a video with natural language is regarded as a fundamental challenge in computer vision. The problem nevertheless is not trivial especially when a video contains multiple events to be worthy of mention, which often happens in real videos. A valid question is how to temporally localize and then describe events, which is known as \"dense video captioning.\" In this paper, we present a novel framework for dense video captioning that unifies the localization of temporal event proposals and sentence generation of each proposal, by jointly training them in an end-to-end manner","authors_text":"Hongyang Chao, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-23T08:18:35Z","title":"Jointly Localizing and Describing Events for Dense Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08274","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:f2f7645c06d15a0a91ac53228a371f416cffddc424818f9ece8391d81b8376cc","target":"record","created_at":"2026-05-18T00:17:48Z","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":"712bf6df9d311bafb4529f55b8704cfe040b2b9cdf5748b0f57eff3226428e61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-23T08:18:35Z","title_canon_sha256":"482c9edeb909115929071b15628b68565e19f6d5337d37c4474798de12fae0a0"},"schema_version":"1.0","source":{"id":"1804.08274","kind":"arxiv","version":1}},"canonical_sha256":"e30bdc69d2498c11069cbc28771394a84ed9d6ae62d0c37f4d085ca0a650d17d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e30bdc69d2498c11069cbc28771394a84ed9d6ae62d0c37f4d085ca0a650d17d","first_computed_at":"2026-05-18T00:17:48.979880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:48.979880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QaecMKlX2lZhSC+aoqZQFrsClYFpA+VDPfv886lLYs/f5ybTO2D5oFIjAll4JdHhlHReuIT7LdxcoQr5xFEcAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:48.980380Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.08274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2f7645c06d15a0a91ac53228a371f416cffddc424818f9ece8391d81b8376cc","sha256:32c5b6fbc4cbdb0c4217db13fe6ebdc95f69e7c0a0567c9b7284c1486a777330"],"state_sha256":"7bf83c73ac143c0cec6baf3df064105cdcd72a1ac7c212ef52427b53b3465ec8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RyhrViqaSXbqzF5WnAe2QWmnXPv7ZZEkYNmYRunaXoUspkQpiwlwu6iGmxaGFfSO6fXpXk7NbkZ7N1S5Y8YDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:21:43.347805Z","bundle_sha256":"7558d306422fe3ed51a8fd9cf90240a8cec0cb6e261d68aa9610d51c0762e1d9"}}