{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6WSZAE5TA4CZIJ5345ZPXY5QE5","short_pith_number":"pith:6WSZAE5T","canonical_record":{"source":{"id":"1901.06829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T09:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"5899b9be485522e7174e24cb6aa8669696626695cee60bc6ae7a389c7ddfdffc","abstract_canon_sha256":"177d22cd0927554db09973845f2c41ac7f9fa0b5687c8f51d56f206cb19f266a"},"schema_version":"1.0"},"canonical_sha256":"f5a59013b307059427bbe772fbe3b027558e9666ffb065dd27780588583af5f2","source":{"kind":"arxiv","id":"1901.06829","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.06829","created_at":"2026-05-17T23:55:49Z"},{"alias_kind":"arxiv_version","alias_value":"1901.06829v1","created_at":"2026-05-17T23:55:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.06829","created_at":"2026-05-17T23:55:49Z"},{"alias_kind":"pith_short_12","alias_value":"6WSZAE5TA4CZ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6WSZAE5TA4CZIJ53","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6WSZAE5T","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6WSZAE5TA4CZIJ5345ZPXY5QE5","target":"record","payload":{"canonical_record":{"source":{"id":"1901.06829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T09:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"5899b9be485522e7174e24cb6aa8669696626695cee60bc6ae7a389c7ddfdffc","abstract_canon_sha256":"177d22cd0927554db09973845f2c41ac7f9fa0b5687c8f51d56f206cb19f266a"},"schema_version":"1.0"},"canonical_sha256":"f5a59013b307059427bbe772fbe3b027558e9666ffb065dd27780588583af5f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:49.031193Z","signature_b64":"DOap0C0HiyzhiweRQiZI2O1Ddf6IvvC934VdzL+NIjnSY6h1UzGA4jQmN9iZ5PV4Cbo76J28NrPCZMD0Y1s2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5a59013b307059427bbe772fbe3b027558e9666ffb065dd27780588583af5f2","last_reissued_at":"2026-05-17T23:55:49.030608Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:49.030608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.06829","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":"2026-05-17T23:55:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JvZSgeTd3Hd/+V9TyrRjGXCoPcmXtaw59o9TZIn8u1X2ev7Z7ckqcbone49unin0lunSEs0flKaAz8Fl1wnzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:24:08.790493Z"},"content_sha256":"35b799e67e269b7af456d819fccfda2205c33f1ccb0c346d3b6b9d30c0b6d110","schema_version":"1.0","event_id":"sha256:35b799e67e269b7af456d819fccfda2205c33f1ccb0c346d3b6b9d30c0b6d110"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6WSZAE5TA4CZIJ5345ZPXY5QE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Fu Li, Jizhou Huang, Shilei Wen, Xiang Zhao, Xiao Liu","submitted_at":"2019-01-21T09:00:11Z","abstract_excerpt":"The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.06829","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":"2026-05-17T23:55:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VqN8cusl8eKo+WaOThHGVN+NUPbHIp4rKsXZ+M7lLix2hFT96C53zl9wlWLgYDk9nHq6i+pLB1FfOIc53cxhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:24:08.790843Z"},"content_sha256":"0e87be8ac8c3233ca4892ddab305b748ac34448d31d04761d9270ee793fdd545","schema_version":"1.0","event_id":"sha256:0e87be8ac8c3233ca4892ddab305b748ac34448d31d04761d9270ee793fdd545"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/bundle.json","state_url":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/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":"2026-05-30T19:24:08Z","links":{"resolver":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5","bundle":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/bundle.json","state":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6WSZAE5TA4CZIJ5345ZPXY5QE5","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":"177d22cd0927554db09973845f2c41ac7f9fa0b5687c8f51d56f206cb19f266a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T09:00:11Z","title_canon_sha256":"5899b9be485522e7174e24cb6aa8669696626695cee60bc6ae7a389c7ddfdffc"},"schema_version":"1.0","source":{"id":"1901.06829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.06829","created_at":"2026-05-17T23:55:49Z"},{"alias_kind":"arxiv_version","alias_value":"1901.06829v1","created_at":"2026-05-17T23:55:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.06829","created_at":"2026-05-17T23:55:49Z"},{"alias_kind":"pith_short_12","alias_value":"6WSZAE5TA4CZ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6WSZAE5TA4CZIJ53","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6WSZAE5T","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:0e87be8ac8c3233ca4892ddab305b748ac34448d31d04761d9270ee793fdd545","target":"graph","created_at":"2026-05-17T23:55:49Z","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":"The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose","authors_text":"Dongliang He, Fu Li, Jizhou Huang, Shilei Wen, Xiang Zhao, Xiao Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T09:00:11Z","title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.06829","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":"sha256:35b799e67e269b7af456d819fccfda2205c33f1ccb0c346d3b6b9d30c0b6d110","target":"record","created_at":"2026-05-17T23:55:49Z","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":"177d22cd0927554db09973845f2c41ac7f9fa0b5687c8f51d56f206cb19f266a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T09:00:11Z","title_canon_sha256":"5899b9be485522e7174e24cb6aa8669696626695cee60bc6ae7a389c7ddfdffc"},"schema_version":"1.0","source":{"id":"1901.06829","kind":"arxiv","version":1}},"canonical_sha256":"f5a59013b307059427bbe772fbe3b027558e9666ffb065dd27780588583af5f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5a59013b307059427bbe772fbe3b027558e9666ffb065dd27780588583af5f2","first_computed_at":"2026-05-17T23:55:49.030608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:49.030608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOap0C0HiyzhiweRQiZI2O1Ddf6IvvC934VdzL+NIjnSY6h1UzGA4jQmN9iZ5PV4Cbo76J28NrPCZMD0Y1s2Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:49.031193Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.06829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35b799e67e269b7af456d819fccfda2205c33f1ccb0c346d3b6b9d30c0b6d110","sha256:0e87be8ac8c3233ca4892ddab305b748ac34448d31d04761d9270ee793fdd545"],"state_sha256":"239d66db4ba2be574782c2f285baf678a9ff9cec7495d9ad048012f886a86f54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ikqgsXoKCok2/vYfZutqIIFNciY3Nm4AqZQu0CjbcKQkSk+9sinmYM4xIpbPxAHa1CD+nklLqypHTxfG17bRAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T19:24:08.792680Z","bundle_sha256":"3af6293b43b3d90e87a70e332bc93c84c71a76ced119c17ce12109cb86a0bfb0"}}