{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CTULJWTT3LSUFF4756UI2POFK4","short_pith_number":"pith:CTULJWTT","canonical_record":{"source":{"id":"2208.09266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T11:21:59Z","cross_cats_sorted":[],"title_canon_sha256":"40d3d70abbcaa878b164a07e4246069635088bf7170ee58f1dcaa78ca0d5ec93","abstract_canon_sha256":"0d0a216a9e60714b769f3fd0822ba1589fbb8f1ccafe380babea266587b4670b"},"schema_version":"1.0"},"canonical_sha256":"14e8b4da73dae542979fefa88d3dc5570b53909458a34e87b38f9f08585adb02","source":{"kind":"arxiv","id":"2208.09266","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.09266","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2208.09266v1","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09266","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"CTULJWTT3LSU","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"CTULJWTT3LSUFF47","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"CTULJWTT","created_at":"2026-07-05T04:49:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CTULJWTT3LSUFF4756UI2POFK4","target":"record","payload":{"canonical_record":{"source":{"id":"2208.09266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T11:21:59Z","cross_cats_sorted":[],"title_canon_sha256":"40d3d70abbcaa878b164a07e4246069635088bf7170ee58f1dcaa78ca0d5ec93","abstract_canon_sha256":"0d0a216a9e60714b769f3fd0822ba1589fbb8f1ccafe380babea266587b4670b"},"schema_version":"1.0"},"canonical_sha256":"14e8b4da73dae542979fefa88d3dc5570b53909458a34e87b38f9f08585adb02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:58.067125Z","signature_b64":"Az387RvD7oISLJcB+GAyEoLdCARTBKNF7cYWTeyKpwi6dghSqPvFMfegB9oan634B8glsPNVUmOc5II7pmJUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14e8b4da73dae542979fefa88d3dc5570b53909458a34e87b38f9f08585adb02","last_reissued_at":"2026-07-05T04:49:58.066705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:58.066705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.09266","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":"2026-07-05T04:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UzGBhUtU1gRxr7U6xJoTCsRRa1GyBIRFmYLtGmsc04bPBLNb1/NmNuGXFsb8qcaayXbNDEbtgk/b2zpQL7lCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:47:44.466549Z"},"content_sha256":"77936a78484bcda0a407b2c8f882150ff105d06ec95a7d3483b3f56c5fa4a276","schema_version":"1.0","event_id":"sha256:77936a78484bcda0a407b2c8f882150ff105d06ec95a7d3483b3f56c5fa4a276"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CTULJWTT3LSUFF4756UI2POFK4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hendrik P. A. Lensch, Leonard Salewski, Zohreh Ghaderi","submitted_at":"2022-08-19T11:21:59Z","abstract_excerpt":"To generate proper captions for videos, the inference needs to identify relevant concepts and pay attention to the spatial relationships between them as well as to the temporal development in the clip. Our end-to-end encoder-decoder video captioning framework incorporates two transformer-based architectures, an adapted transformer for a single joint spatio-temporal video analysis as well as a self-attention-based decoder for advanced text generation. Furthermore, we introduce an adaptive frame selection scheme to reduce the number of required incoming frames while maintaining the relevant cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09266","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/2208.09266/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r/POQv9zNHIiqRQe185xiMJk7IsCYWp75BiGyymshA5d+hjAZpitnyKcuDjtuCzQU2SnFtY552bGZPrjIscfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:47:44.466923Z"},"content_sha256":"bfc8a359026f765c3bffb2e675c10009ace400b898b3c01fd09161cd0ed5e053","schema_version":"1.0","event_id":"sha256:bfc8a359026f765c3bffb2e675c10009ace400b898b3c01fd09161cd0ed5e053"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTULJWTT3LSUFF4756UI2POFK4/bundle.json","state_url":"https://pith.science/pith/CTULJWTT3LSUFF4756UI2POFK4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTULJWTT3LSUFF4756UI2POFK4/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":"2026-07-09T04:47:44Z","links":{"resolver":"https://pith.science/pith/CTULJWTT3LSUFF4756UI2POFK4","bundle":"https://pith.science/pith/CTULJWTT3LSUFF4756UI2POFK4/bundle.json","state":"https://pith.science/pith/CTULJWTT3LSUFF4756UI2POFK4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTULJWTT3LSUFF4756UI2POFK4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CTULJWTT3LSUFF4756UI2POFK4","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":"0d0a216a9e60714b769f3fd0822ba1589fbb8f1ccafe380babea266587b4670b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T11:21:59Z","title_canon_sha256":"40d3d70abbcaa878b164a07e4246069635088bf7170ee58f1dcaa78ca0d5ec93"},"schema_version":"1.0","source":{"id":"2208.09266","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.09266","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2208.09266v1","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09266","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"CTULJWTT3LSU","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"CTULJWTT3LSUFF47","created_at":"2026-07-05T04:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"CTULJWTT","created_at":"2026-07-05T04:49:58Z"}],"graph_snapshots":[{"event_id":"sha256:bfc8a359026f765c3bffb2e675c10009ace400b898b3c01fd09161cd0ed5e053","target":"graph","created_at":"2026-07-05T04:49:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.09266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To generate proper captions for videos, the inference needs to identify relevant concepts and pay attention to the spatial relationships between them as well as to the temporal development in the clip. Our end-to-end encoder-decoder video captioning framework incorporates two transformer-based architectures, an adapted transformer for a single joint spatio-temporal video analysis as well as a self-attention-based decoder for advanced text generation. Furthermore, we introduce an adaptive frame selection scheme to reduce the number of required incoming frames while maintaining the relevant cont","authors_text":"Hendrik P. A. Lensch, Leonard Salewski, Zohreh Ghaderi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T11:21:59Z","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09266","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":"sha256:77936a78484bcda0a407b2c8f882150ff105d06ec95a7d3483b3f56c5fa4a276","target":"record","created_at":"2026-07-05T04:49:58Z","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":"0d0a216a9e60714b769f3fd0822ba1589fbb8f1ccafe380babea266587b4670b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T11:21:59Z","title_canon_sha256":"40d3d70abbcaa878b164a07e4246069635088bf7170ee58f1dcaa78ca0d5ec93"},"schema_version":"1.0","source":{"id":"2208.09266","kind":"arxiv","version":1}},"canonical_sha256":"14e8b4da73dae542979fefa88d3dc5570b53909458a34e87b38f9f08585adb02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14e8b4da73dae542979fefa88d3dc5570b53909458a34e87b38f9f08585adb02","first_computed_at":"2026-07-05T04:49:58.066705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:49:58.066705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Az387RvD7oISLJcB+GAyEoLdCARTBKNF7cYWTeyKpwi6dghSqPvFMfegB9oan634B8glsPNVUmOc5II7pmJUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:49:58.067125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.09266","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77936a78484bcda0a407b2c8f882150ff105d06ec95a7d3483b3f56c5fa4a276","sha256:bfc8a359026f765c3bffb2e675c10009ace400b898b3c01fd09161cd0ed5e053"],"state_sha256":"799b5b19742674cd14fc1b264c59ffadcea925a80b55a0493f920e0ee03fdc2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8JTB2tQME0ZzXpIqC73zTcZwF1WQlLkdbr+arcaofsp6/ZQLLbJMZ2Jusi4q0l6RLIOft2fIKxifrmJ8fkdbBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:47:44.468870Z","bundle_sha256":"c428a10cfa3eb6fa584df5e592c64cea08d7a46b4c99c5dd93dd733ed8c41a8a"}}