{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VLUPD2YQLNQXCRXH57IOX5PREI","short_pith_number":"pith:VLUPD2YQ","schema_version":"1.0","canonical_sha256":"aae8f1eb105b617146e7efd0ebf5f1223a5f3c9b7460c98d70597ebf435ab695","source":{"kind":"arxiv","id":"1910.11631","version":1},"attestation_state":"computed","paper":{"title":"Learning to Localize Temporal Events in Large-scale Video Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Austin, Miha Skalic, Mikel Bober-Irizar","submitted_at":"2019-10-25T11:40:29Z","abstract_excerpt":"We address temporal localization of events in large-scale video data, in the context of the Youtube-8M Segments dataset. This emerging field within video recognition can enable applications to identify the precise time a specified event occurs in a video, which has broad implications for video search. To address this we present two separate approaches: (1) a gradient boosted decision tree model on a crafted dataset and (2) a combination of deep learning models based on frame-level data, video-level data, and a localization model. The combinations of these two approaches achieved 5th place in t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1910.11631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-25T11:40:29Z","cross_cats_sorted":[],"title_canon_sha256":"44ec0c33ca539ff445914480bb3ce76d7683a6572bca38d273d9578093537423","abstract_canon_sha256":"9223e4b4139953951686de6a686ea944a5b63ade8aca777e508d39bdc48b4b4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:55.619840Z","signature_b64":"0tiKANEC4VafsP34IjOETvIAwX+Iyq8KHGfDUpuE1PScbzX952BPrirY5H5zIaxpav1IYZ54Q1ey1G/b0+QGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aae8f1eb105b617146e7efd0ebf5f1223a5f3c9b7460c98d70597ebf435ab695","last_reissued_at":"2026-07-05T00:14:55.619373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:55.619373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Localize Temporal Events in Large-scale Video Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Austin, Miha Skalic, Mikel Bober-Irizar","submitted_at":"2019-10-25T11:40:29Z","abstract_excerpt":"We address temporal localization of events in large-scale video data, in the context of the Youtube-8M Segments dataset. This emerging field within video recognition can enable applications to identify the precise time a specified event occurs in a video, which has broad implications for video search. To address this we present two separate approaches: (1) a gradient boosted decision tree model on a crafted dataset and (2) a combination of deep learning models based on frame-level data, video-level data, and a localization model. The combinations of these two approaches achieved 5th place in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.11631","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.11631/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1910.11631","created_at":"2026-07-05T00:14:55.619434+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.11631v1","created_at":"2026-07-05T00:14:55.619434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.11631","created_at":"2026-07-05T00:14:55.619434+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLUPD2YQLNQX","created_at":"2026-07-05T00:14:55.619434+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLUPD2YQLNQXCRXH","created_at":"2026-07-05T00:14:55.619434+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLUPD2YQ","created_at":"2026-07-05T00:14:55.619434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06219","citing_title":"WhACC: Whisker Automatic Contact Classifier with Expert Human-Level Performance","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI","json":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI.json","graph_json":"https://pith.science/api/pith-number/VLUPD2YQLNQXCRXH57IOX5PREI/graph.json","events_json":"https://pith.science/api/pith-number/VLUPD2YQLNQXCRXH57IOX5PREI/events.json","paper":"https://pith.science/paper/VLUPD2YQ"},"agent_actions":{"view_html":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI","download_json":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI.json","view_paper":"https://pith.science/paper/VLUPD2YQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.11631&json=true","fetch_graph":"https://pith.science/api/pith-number/VLUPD2YQLNQXCRXH57IOX5PREI/graph.json","fetch_events":"https://pith.science/api/pith-number/VLUPD2YQLNQXCRXH57IOX5PREI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI/action/storage_attestation","attest_author":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI/action/author_attestation","sign_citation":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI/action/citation_signature","submit_replication":"https://pith.science/pith/VLUPD2YQLNQXCRXH57IOX5PREI/action/replication_record"}},"created_at":"2026-07-05T00:14:55.619434+00:00","updated_at":"2026-07-05T00:14:55.619434+00:00"}