{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:USYZNZBSUAHLFLYOHTJUFJRXYQ","short_pith_number":"pith:USYZNZBS","canonical_record":{"source":{"id":"1611.07837","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-23T15:21:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"48869c6d0e240e01e80175af99a3782145879b2c63d715ccc1a3c518faa690dd","abstract_canon_sha256":"49adc070d6849f126e7853cbe532d4aeb8e31f2cec92d3ec7f4053df240a52e6"},"schema_version":"1.0"},"canonical_sha256":"a4b196e432a00eb2af0e3cd342a637c411be6c816245923d1a34546fd1ed11a3","source":{"kind":"arxiv","id":"1611.07837","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.07837","created_at":"2026-05-18T00:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"1611.07837v3","created_at":"2026-05-18T00:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07837","created_at":"2026-05-18T00:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"USYZNZBSUAHL","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"USYZNZBSUAHLFLYO","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"USYZNZBS","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:USYZNZBSUAHLFLYOHTJUFJRXYQ","target":"record","payload":{"canonical_record":{"source":{"id":"1611.07837","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-23T15:21:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"48869c6d0e240e01e80175af99a3782145879b2c63d715ccc1a3c518faa690dd","abstract_canon_sha256":"49adc070d6849f126e7853cbe532d4aeb8e31f2cec92d3ec7f4053df240a52e6"},"schema_version":"1.0"},"canonical_sha256":"a4b196e432a00eb2af0e3cd342a637c411be6c816245923d1a34546fd1ed11a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:22.464703Z","signature_b64":"bYjBckNbNV4QCJnwQ+KqOQ++aBfB0Pqgg7U6JULRrutQEbCdDc23znJVYjyGYc2E55zKQPZJI7Pn9uiGpHE6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4b196e432a00eb2af0e3cd342a637c411be6c816245923d1a34546fd1ed11a3","last_reissued_at":"2026-05-18T00:30:22.463845Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:22.463845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.07837","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":"2026-05-18T00:30:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bNHZmX4kU0i2yhpZyU+Q1lrwh/KzeO1IDKjJzviPhZF/LSjqt14BU9pdmhfAwKgesud+QDHZf+sgHshy4h8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:52:33.026531Z"},"content_sha256":"b7d31f31a1ea8be8d70d43b0c767f8e64c6de184fde50522557e94099873da5c","schema_version":"1.0","event_id":"sha256:b7d31f31a1ea8be8d70d43b0c767f8e64c6de184fde50522557e94099873da5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:USYZNZBSUAHLFLYOHTJUFJRXYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Feature Abstraction for Translating Video to Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lawrence Carin, Martin Renqiang Min, Yunchen Pu, Zhe Gan","submitted_at":"2016-11-23T15:21:48Z","abstract_excerpt":"Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features. However, the variable context-dependent semantics in the video may make it more appropriate to adaptively select features from the multiple CNN layers. We propose a new approach for generating adaptive spatiotemporal representations of videos for the captioning task. A novel attention mechanism is developed, that adaptively and sequentially focuses on different layers of CNN features (levels of feature \"abstraction\"), as well as local spatiotemporal regions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07837","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":"2026-05-18T00:30:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SRJlehoZ+OLRIzuRrWLRFRHj+uavRk5STjVcu+CG4kag2VYZvK631lGKOIJElft8K76OZ1dnyKeCGysYKgloBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:52:33.026884Z"},"content_sha256":"12893460108dc3e1a11806a09e5b17aef8ea1085cb9be50689947a043b27e4b9","schema_version":"1.0","event_id":"sha256:12893460108dc3e1a11806a09e5b17aef8ea1085cb9be50689947a043b27e4b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USYZNZBSUAHLFLYOHTJUFJRXYQ/bundle.json","state_url":"https://pith.science/pith/USYZNZBSUAHLFLYOHTJUFJRXYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USYZNZBSUAHLFLYOHTJUFJRXYQ/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":"2026-06-02T11:52:33Z","links":{"resolver":"https://pith.science/pith/USYZNZBSUAHLFLYOHTJUFJRXYQ","bundle":"https://pith.science/pith/USYZNZBSUAHLFLYOHTJUFJRXYQ/bundle.json","state":"https://pith.science/pith/USYZNZBSUAHLFLYOHTJUFJRXYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USYZNZBSUAHLFLYOHTJUFJRXYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:USYZNZBSUAHLFLYOHTJUFJRXYQ","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":"49adc070d6849f126e7853cbe532d4aeb8e31f2cec92d3ec7f4053df240a52e6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-23T15:21:48Z","title_canon_sha256":"48869c6d0e240e01e80175af99a3782145879b2c63d715ccc1a3c518faa690dd"},"schema_version":"1.0","source":{"id":"1611.07837","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.07837","created_at":"2026-05-18T00:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"1611.07837v3","created_at":"2026-05-18T00:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07837","created_at":"2026-05-18T00:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"USYZNZBSUAHL","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"USYZNZBSUAHLFLYO","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"USYZNZBS","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:12893460108dc3e1a11806a09e5b17aef8ea1085cb9be50689947a043b27e4b9","target":"graph","created_at":"2026-05-18T00:30:22Z","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":"Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features. However, the variable context-dependent semantics in the video may make it more appropriate to adaptively select features from the multiple CNN layers. We propose a new approach for generating adaptive spatiotemporal representations of videos for the captioning task. A novel attention mechanism is developed, that adaptively and sequentially focuses on different layers of CNN features (levels of feature \"abstraction\"), as well as local spatiotemporal regions","authors_text":"Lawrence Carin, Martin Renqiang Min, Yunchen Pu, Zhe Gan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-23T15:21:48Z","title":"Adaptive Feature Abstraction for Translating Video to Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07837","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:b7d31f31a1ea8be8d70d43b0c767f8e64c6de184fde50522557e94099873da5c","target":"record","created_at":"2026-05-18T00:30:22Z","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":"49adc070d6849f126e7853cbe532d4aeb8e31f2cec92d3ec7f4053df240a52e6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-23T15:21:48Z","title_canon_sha256":"48869c6d0e240e01e80175af99a3782145879b2c63d715ccc1a3c518faa690dd"},"schema_version":"1.0","source":{"id":"1611.07837","kind":"arxiv","version":3}},"canonical_sha256":"a4b196e432a00eb2af0e3cd342a637c411be6c816245923d1a34546fd1ed11a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4b196e432a00eb2af0e3cd342a637c411be6c816245923d1a34546fd1ed11a3","first_computed_at":"2026-05-18T00:30:22.463845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:22.463845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bYjBckNbNV4QCJnwQ+KqOQ++aBfB0Pqgg7U6JULRrutQEbCdDc23znJVYjyGYc2E55zKQPZJI7Pn9uiGpHE6CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:22.464703Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.07837","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7d31f31a1ea8be8d70d43b0c767f8e64c6de184fde50522557e94099873da5c","sha256:12893460108dc3e1a11806a09e5b17aef8ea1085cb9be50689947a043b27e4b9"],"state_sha256":"c66514061f93b59fea0d6b311541ce0f0b144a1efa4871ef8623e2766d1f2291"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/nS1qcU+QbLmatccQBN4CygTGW1G+biDVYaXvKWyKWRMnF9zlCPz3s0dAOp5odxkFeI5fiB5ugDvYMhBV0uDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:52:33.028865Z","bundle_sha256":"f2ea10ab2da107025042c2753a0597bd67e7670c5e0b7dcb859b53fa24003e82"}}