{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BSNFBLYE5A5LI3D7U3KZBXQYWZ","short_pith_number":"pith:BSNFBLYE","canonical_record":{"source":{"id":"1711.11135","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-29T22:23:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d54f386cd25e4e7c3d6078fe47301c84826de776a780565cb111d4dfa6924b73","abstract_canon_sha256":"e5c3369d7b7b6ff718c48896d0a6537ab0d5a0d71d5ef1707fec66306a3d1f63"},"schema_version":"1.0"},"canonical_sha256":"0c9a50af04e83ab46c7fa6d590de18b655e0c9069d73244d294679ec5cf3d95a","source":{"kind":"arxiv","id":"1711.11135","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.11135","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"1711.11135v3","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11135","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"BSNFBLYE5A5L","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BSNFBLYE5A5LI3D7","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BSNFBLYE","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BSNFBLYE5A5LI3D7U3KZBXQYWZ","target":"record","payload":{"canonical_record":{"source":{"id":"1711.11135","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-29T22:23:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d54f386cd25e4e7c3d6078fe47301c84826de776a780565cb111d4dfa6924b73","abstract_canon_sha256":"e5c3369d7b7b6ff718c48896d0a6537ab0d5a0d71d5ef1707fec66306a3d1f63"},"schema_version":"1.0"},"canonical_sha256":"0c9a50af04e83ab46c7fa6d590de18b655e0c9069d73244d294679ec5cf3d95a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:53.308835Z","signature_b64":"eQE4S+TR4NkGwKyh79TWOAak6pV/lBMl3HEMfTsPPNNsM4Qu8KxbDY9w8lcGnKswYKVs43JuvoD3lKrWK+T2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c9a50af04e83ab46c7fa6d590de18b655e0c9069d73244d294679ec5cf3d95a","last_reissued_at":"2026-05-18T00:19:53.308158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:53.308158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.11135","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":"2026-05-18T00:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MBo+cRl+Cu44Dx/doVuZNR9FWp1fwDCI+snGHHYhDrjunJxrn8LpeNPvN/L2fkJhurFPLWHl+jUrLL+8oQSaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:18:12.200924Z"},"content_sha256":"bb80c78f114ec82daa4adf197b4e0749cbd7ed136a7b129feedf84a5de98bf2d","schema_version":"1.0","event_id":"sha256:bb80c78f114ec82daa4adf197b4e0749cbd7ed136a7b129feedf84a5de98bf2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BSNFBLYE5A5LI3D7U3KZBXQYWZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Captioning via Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiawei Wu, Wenhu Chen, William Yang Wang, Xin Wang, Yuan-Fang Wang","submitted_at":"2017-11-29T22:23:59Z","abstract_excerpt":"Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is still very challenging to caption a video containing multiple fine-grained actions with a detailed description. This paper aims to address the challenge by proposing a novel hierarchical reinforcement learning framework for video captioning, where a high-level Manager module learns to design sub-goals and a low-level Worker module recognizes the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11135","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":"2026-05-18T00:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXUMgYExcIX3R/8d0G7/NY/P+W/T6D2yMc3vn9FqN+q+2do2xuzeYLcPRIkLeVZDW6DEWC8upp/zLphsL7ndBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:18:12.201594Z"},"content_sha256":"be3cd141d86a1f473fb1397c11633b9a91c744a800a6b67e1de92df0ed87e5b2","schema_version":"1.0","event_id":"sha256:be3cd141d86a1f473fb1397c11633b9a91c744a800a6b67e1de92df0ed87e5b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSNFBLYE5A5LI3D7U3KZBXQYWZ/bundle.json","state_url":"https://pith.science/pith/BSNFBLYE5A5LI3D7U3KZBXQYWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSNFBLYE5A5LI3D7U3KZBXQYWZ/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":"2026-06-06T14:18:12Z","links":{"resolver":"https://pith.science/pith/BSNFBLYE5A5LI3D7U3KZBXQYWZ","bundle":"https://pith.science/pith/BSNFBLYE5A5LI3D7U3KZBXQYWZ/bundle.json","state":"https://pith.science/pith/BSNFBLYE5A5LI3D7U3KZBXQYWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSNFBLYE5A5LI3D7U3KZBXQYWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BSNFBLYE5A5LI3D7U3KZBXQYWZ","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":"e5c3369d7b7b6ff718c48896d0a6537ab0d5a0d71d5ef1707fec66306a3d1f63","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-29T22:23:59Z","title_canon_sha256":"d54f386cd25e4e7c3d6078fe47301c84826de776a780565cb111d4dfa6924b73"},"schema_version":"1.0","source":{"id":"1711.11135","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.11135","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"1711.11135v3","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11135","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"BSNFBLYE5A5L","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BSNFBLYE5A5LI3D7","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BSNFBLYE","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:be3cd141d86a1f473fb1397c11633b9a91c744a800a6b67e1de92df0ed87e5b2","target":"graph","created_at":"2026-05-18T00:19:53Z","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 captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is still very challenging to caption a video containing multiple fine-grained actions with a detailed description. This paper aims to address the challenge by proposing a novel hierarchical reinforcement learning framework for video captioning, where a high-level Manager module learns to design sub-goals and a low-level Worker module recognizes the p","authors_text":"Jiawei Wu, Wenhu Chen, William Yang Wang, Xin Wang, Yuan-Fang Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-29T22:23:59Z","title":"Video Captioning via Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11135","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:bb80c78f114ec82daa4adf197b4e0749cbd7ed136a7b129feedf84a5de98bf2d","target":"record","created_at":"2026-05-18T00:19:53Z","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":"e5c3369d7b7b6ff718c48896d0a6537ab0d5a0d71d5ef1707fec66306a3d1f63","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-29T22:23:59Z","title_canon_sha256":"d54f386cd25e4e7c3d6078fe47301c84826de776a780565cb111d4dfa6924b73"},"schema_version":"1.0","source":{"id":"1711.11135","kind":"arxiv","version":3}},"canonical_sha256":"0c9a50af04e83ab46c7fa6d590de18b655e0c9069d73244d294679ec5cf3d95a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c9a50af04e83ab46c7fa6d590de18b655e0c9069d73244d294679ec5cf3d95a","first_computed_at":"2026-05-18T00:19:53.308158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:53.308158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eQE4S+TR4NkGwKyh79TWOAak6pV/lBMl3HEMfTsPPNNsM4Qu8KxbDY9w8lcGnKswYKVs43JuvoD3lKrWK+T2Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:53.308835Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.11135","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb80c78f114ec82daa4adf197b4e0749cbd7ed136a7b129feedf84a5de98bf2d","sha256:be3cd141d86a1f473fb1397c11633b9a91c744a800a6b67e1de92df0ed87e5b2"],"state_sha256":"31ffae3a9c5c56ce3789d22f8a1d056d3b5c8bf67548182e6dd31370bee13f5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X2JbHLIJz8bysqg9faZNNmH3JVASMTAK9M/Dhrd4pOi6QWLVoL3VOiWXJzVzDvBkvwMatVuYedP27VHfmDEYCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T14:18:12.205476Z","bundle_sha256":"cefd3bb8233a36485ffdac1a57c6f005de27532fabf26244c31e3c3547ba0c8a"}}