{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:B5LRDKAECSWMCLWFXEKNQYVYTA","short_pith_number":"pith:B5LRDKAE","canonical_record":{"source":{"id":"1403.6173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-03-24T22:28:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9efe9f71b1ddccda470c5004465c846f652180b15b619814fa5def5fa450cbfb","abstract_canon_sha256":"ab930c77cc220b89cb03fbad862150fe2f69be564db95cbe952bc20083a5161d"},"schema_version":"1.0"},"canonical_sha256":"0f5711a80414acc12ec5b914d862b8981ae27489ef27f1a6cf2ec176a4c4b173","source":{"kind":"arxiv","id":"1403.6173","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.6173","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"1403.6173v1","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.6173","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"B5LRDKAECSWM","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"B5LRDKAECSWMCLWF","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"B5LRDKAE","created_at":"2026-05-18T12:28:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:B5LRDKAECSWMCLWFXEKNQYVYTA","target":"record","payload":{"canonical_record":{"source":{"id":"1403.6173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-03-24T22:28:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9efe9f71b1ddccda470c5004465c846f652180b15b619814fa5def5fa450cbfb","abstract_canon_sha256":"ab930c77cc220b89cb03fbad862150fe2f69be564db95cbe952bc20083a5161d"},"schema_version":"1.0"},"canonical_sha256":"0f5711a80414acc12ec5b914d862b8981ae27489ef27f1a6cf2ec176a4c4b173","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:04.365290Z","signature_b64":"e5lNIEQQRIVtD87g3X+3U1wHl2WhNmNXgFxct84+Kt7oRZdqYPaWSI1qoCb4rVm/MGHp9hLH5zfIy7zsDFSjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f5711a80414acc12ec5b914d862b8981ae27489ef27f1a6cf2ec176a4c4b173","last_reissued_at":"2026-05-18T01:04:04.364912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:04.364912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1403.6173","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":"2026-05-18T01:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hwCS15T+ww513OGQlPBjVGCuTbbXeXh7PqWqAZfivpAHRLs40u6ED1Bkne5ZwjXwU5nNWYrLT7G/F/ReFeXsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T16:36:31.059694Z"},"content_sha256":"ba53a001ef5cdec55881526d496ae762c7b47812c20e956ccb0c4e1109c53d8f","schema_version":"1.0","event_id":"sha256:ba53a001ef5cdec55881526d496ae762c7b47812c20e956ccb0c4e1109c53d8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:B5LRDKAECSWMCLWFXEKNQYVYTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Senina, Annemarie Friedrich, Bernt Schiele, Manfred Pinkal, Marcus Rohrbach, Mykhaylo Andriluka, Sikandar Amin, Wei Qiu","submitted_at":"2014-03-24T22:28:38Z","abstract_excerpt":"Humans can easily describe what they see in a coherent way and at varying level of detail. However, existing approaches for automatic video description are mainly focused on single sentence generation and produce descriptions at a fixed level of detail. In this paper, we address both of these limitations: for a variable level of detail we produce coherent multi-sentence descriptions of complex videos. We follow a two-step approach where we first learn to predict a semantic representation (SR) from video and then generate natural language descriptions from the SR. To produce consistent multi-se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.6173","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":"2026-05-18T01:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buEIrfPIInw8q+Aqgf6ZFxTBr/qYKc0/Mg56qrVfWr1DGq9iI19CqoYSU5Bsd5n1BzL7rE0p7LoA58MPp+/9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T16:36:31.060038Z"},"content_sha256":"b7457f069bf46e641cc67728ef770bb812032344ce067cb1b9262b23d2f9f02f","schema_version":"1.0","event_id":"sha256:b7457f069bf46e641cc67728ef770bb812032344ce067cb1b9262b23d2f9f02f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/bundle.json","state_url":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/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":"2026-05-19T16:36:31Z","links":{"resolver":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA","bundle":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/bundle.json","state":"https://pith.science/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5LRDKAECSWMCLWFXEKNQYVYTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:B5LRDKAECSWMCLWFXEKNQYVYTA","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":"ab930c77cc220b89cb03fbad862150fe2f69be564db95cbe952bc20083a5161d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-03-24T22:28:38Z","title_canon_sha256":"9efe9f71b1ddccda470c5004465c846f652180b15b619814fa5def5fa450cbfb"},"schema_version":"1.0","source":{"id":"1403.6173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.6173","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"1403.6173v1","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.6173","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"B5LRDKAECSWM","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"B5LRDKAECSWMCLWF","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"B5LRDKAE","created_at":"2026-05-18T12:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:b7457f069bf46e641cc67728ef770bb812032344ce067cb1b9262b23d2f9f02f","target":"graph","created_at":"2026-05-18T01:04:04Z","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":"Humans can easily describe what they see in a coherent way and at varying level of detail. However, existing approaches for automatic video description are mainly focused on single sentence generation and produce descriptions at a fixed level of detail. In this paper, we address both of these limitations: for a variable level of detail we produce coherent multi-sentence descriptions of complex videos. We follow a two-step approach where we first learn to predict a semantic representation (SR) from video and then generate natural language descriptions from the SR. To produce consistent multi-se","authors_text":"Anna Senina, Annemarie Friedrich, Bernt Schiele, Manfred Pinkal, Marcus Rohrbach, Mykhaylo Andriluka, Sikandar Amin, Wei Qiu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-03-24T22:28:38Z","title":"Coherent Multi-Sentence Video Description with Variable Level of Detail"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.6173","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:ba53a001ef5cdec55881526d496ae762c7b47812c20e956ccb0c4e1109c53d8f","target":"record","created_at":"2026-05-18T01:04:04Z","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":"ab930c77cc220b89cb03fbad862150fe2f69be564db95cbe952bc20083a5161d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-03-24T22:28:38Z","title_canon_sha256":"9efe9f71b1ddccda470c5004465c846f652180b15b619814fa5def5fa450cbfb"},"schema_version":"1.0","source":{"id":"1403.6173","kind":"arxiv","version":1}},"canonical_sha256":"0f5711a80414acc12ec5b914d862b8981ae27489ef27f1a6cf2ec176a4c4b173","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f5711a80414acc12ec5b914d862b8981ae27489ef27f1a6cf2ec176a4c4b173","first_computed_at":"2026-05-18T01:04:04.364912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:04.364912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e5lNIEQQRIVtD87g3X+3U1wHl2WhNmNXgFxct84+Kt7oRZdqYPaWSI1qoCb4rVm/MGHp9hLH5zfIy7zsDFSjAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:04.365290Z","signed_message":"canonical_sha256_bytes"},"source_id":"1403.6173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba53a001ef5cdec55881526d496ae762c7b47812c20e956ccb0c4e1109c53d8f","sha256:b7457f069bf46e641cc67728ef770bb812032344ce067cb1b9262b23d2f9f02f"],"state_sha256":"4fb895ba13e8f6a541835c4fcd44ee7cef8aac885192c476c8c921313564f978"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QpJl+ZrNsrS7NtcdUFFKVbwQ/JeGA+pSyI7krD1QzYnehGzZRaPYTi2FehSajFy8DLZxlKJkJ6UfyLbLPxexDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T16:36:31.062030Z","bundle_sha256":"1eca0177d902383c8b88b369716c90cc314de1f8b02237926cd849cec9586229"}}