{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HTY37T2SFOGNOROL5RDVZPPIHW","short_pith_number":"pith:HTY37T2S","canonical_record":{"source":{"id":"1804.05113","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T20:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"2e03ab46150dfe7778b442a5aa8cb091d9250da54a403af9139d141dd9730067","abstract_canon_sha256":"fe6229ef8522b501147274619e283ea2aac056acf497ad23d5a63cfe52f5fcd2"},"schema_version":"1.0"},"canonical_sha256":"3cf1bfcf522b8cd745cbec475cbde83d8e8ae1ebb0f32beb6469b552bbab8142","source":{"kind":"arxiv","id":"1804.05113","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05113","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05113v3","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05113","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"HTY37T2SFOGN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HTY37T2SFOGNOROL","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HTY37T2S","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HTY37T2SFOGNOROL5RDVZPPIHW","target":"record","payload":{"canonical_record":{"source":{"id":"1804.05113","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T20:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"2e03ab46150dfe7778b442a5aa8cb091d9250da54a403af9139d141dd9730067","abstract_canon_sha256":"fe6229ef8522b501147274619e283ea2aac056acf497ad23d5a63cfe52f5fcd2"},"schema_version":"1.0"},"canonical_sha256":"3cf1bfcf522b8cd745cbec475cbde83d8e8ae1ebb0f32beb6469b552bbab8142","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:32.050780Z","signature_b64":"VF5aDz6DVjOWVAR66HQC6cU1bHA4iWVyKgbadkG553LAOMB3F0ZIiBL3BLduHHOqZp5mBnTBO30n0TqDMmZ+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cf1bfcf522b8cd745cbec475cbde83d8e8ae1ebb0f32beb6469b552bbab8142","last_reissued_at":"2026-05-17T23:57:32.050070Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:32.050070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.05113","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfczBk2M6ztb9tZ+OhZKeJXO6FPQy0bnw2OhA3uJiYOhTfueTfb2WBtXaReVc7l1ihYgAE5zTWdiq7u8+LFKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:56:16.763182Z"},"content_sha256":"f01515439d045f12724bc39ecfdccf55eaf71ecf34bd119fc2b1ca2e25ff4e76","schema_version":"1.0","event_id":"sha256:f01515439d045f12724bc39ecfdccf55eaf71ecf34bd119fc2b1ca2e25ff4e76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HTY37T2SFOGNOROL5RDVZPPIHW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bryan A. Plummer, Huijuan Xu, Kate Saenko, Kun He, Leonid Sigal, Stan Sclaroff","submitted_at":"2018-04-13T20:46:37Z","abstract_excerpt":"We address the problem of text-based activity retrieval in video. Given a sentence describing an activity, our task is to retrieve matching clips from an untrimmed video. To capture the inherent structures present in both text and video, we introduce a multilevel model that integrates vision and language features earlier and more tightly than prior work. First, we inject text features early on when generating clip proposals, to help eliminate unlikely clips and thus speed up processing and boost performance. Second, to learn a fine-grained similarity metric for retrieval, we use visual feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05113","kind":"arxiv","version":3},"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":"2026-05-17T23:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J3v8azptcnwyBk0V8247eDcm8x618Dr4pDXtCM8tLQQhfFeLYKOmmIoozxpXI8thMgzRzIKh9aeKAzXYU1ZEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:56:16.763873Z"},"content_sha256":"54deb784b02e31f0adb18f9878440c00440fd3631bd6251d8a03d1a740fe0248","schema_version":"1.0","event_id":"sha256:54deb784b02e31f0adb18f9878440c00440fd3631bd6251d8a03d1a740fe0248"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTY37T2SFOGNOROL5RDVZPPIHW/bundle.json","state_url":"https://pith.science/pith/HTY37T2SFOGNOROL5RDVZPPIHW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTY37T2SFOGNOROL5RDVZPPIHW/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":"2026-05-25T16:56:16Z","links":{"resolver":"https://pith.science/pith/HTY37T2SFOGNOROL5RDVZPPIHW","bundle":"https://pith.science/pith/HTY37T2SFOGNOROL5RDVZPPIHW/bundle.json","state":"https://pith.science/pith/HTY37T2SFOGNOROL5RDVZPPIHW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTY37T2SFOGNOROL5RDVZPPIHW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HTY37T2SFOGNOROL5RDVZPPIHW","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":"fe6229ef8522b501147274619e283ea2aac056acf497ad23d5a63cfe52f5fcd2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T20:46:37Z","title_canon_sha256":"2e03ab46150dfe7778b442a5aa8cb091d9250da54a403af9139d141dd9730067"},"schema_version":"1.0","source":{"id":"1804.05113","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05113","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05113v3","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05113","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"HTY37T2SFOGN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HTY37T2SFOGNOROL","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HTY37T2S","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:54deb784b02e31f0adb18f9878440c00440fd3631bd6251d8a03d1a740fe0248","target":"graph","created_at":"2026-05-17T23:57:32Z","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":"We address the problem of text-based activity retrieval in video. Given a sentence describing an activity, our task is to retrieve matching clips from an untrimmed video. To capture the inherent structures present in both text and video, we introduce a multilevel model that integrates vision and language features earlier and more tightly than prior work. First, we inject text features early on when generating clip proposals, to help eliminate unlikely clips and thus speed up processing and boost performance. Second, to learn a fine-grained similarity metric for retrieval, we use visual feature","authors_text":"Bryan A. Plummer, Huijuan Xu, Kate Saenko, Kun He, Leonid Sigal, Stan Sclaroff","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T20:46:37Z","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05113","kind":"arxiv","version":3},"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:f01515439d045f12724bc39ecfdccf55eaf71ecf34bd119fc2b1ca2e25ff4e76","target":"record","created_at":"2026-05-17T23:57:32Z","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":"fe6229ef8522b501147274619e283ea2aac056acf497ad23d5a63cfe52f5fcd2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T20:46:37Z","title_canon_sha256":"2e03ab46150dfe7778b442a5aa8cb091d9250da54a403af9139d141dd9730067"},"schema_version":"1.0","source":{"id":"1804.05113","kind":"arxiv","version":3}},"canonical_sha256":"3cf1bfcf522b8cd745cbec475cbde83d8e8ae1ebb0f32beb6469b552bbab8142","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cf1bfcf522b8cd745cbec475cbde83d8e8ae1ebb0f32beb6469b552bbab8142","first_computed_at":"2026-05-17T23:57:32.050070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:32.050070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VF5aDz6DVjOWVAR66HQC6cU1bHA4iWVyKgbadkG553LAOMB3F0ZIiBL3BLduHHOqZp5mBnTBO30n0TqDMmZ+DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:32.050780Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.05113","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f01515439d045f12724bc39ecfdccf55eaf71ecf34bd119fc2b1ca2e25ff4e76","sha256:54deb784b02e31f0adb18f9878440c00440fd3631bd6251d8a03d1a740fe0248"],"state_sha256":"a378f733c94bf29e0b38892ddf4cc4593e69d24f27a7b56bc571a633e456f9f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zm9cP97b1WvaWA2j5CVQpsuUpM7mpc2Cwdvo9v0aiZUVrVt2jZD1cKYgGHjAyQ7KLYu9QQIGSeyQXy3cd9FeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:56:16.767903Z","bundle_sha256":"8835fe0d240dd1e3f0e926a4ac6acc4dcfb619e9fd7ca7ed6c21ed998f293b23"}}