{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FGW7ZZD2PIFWM2AMHNK7HWX7HY","short_pith_number":"pith:FGW7ZZD2","canonical_record":{"source":{"id":"1411.4389","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-17T08:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"cee88a093cf6888a0e030bcce3d8bb67bce07045037d2cb1e520aa6b1ecd8451","abstract_canon_sha256":"d9dfa9ef27e263d585432d346c4c46ca9e708849f33ea963eaef052dcebaccfd"},"schema_version":"1.0"},"canonical_sha256":"29adfce47a7a0b66680c3b55f3daff3e1cbe95d81106e50ac9ddd2eb242f6aff","source":{"kind":"arxiv","id":"1411.4389","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.4389","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"arxiv_version","alias_value":"1411.4389v4","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.4389","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"pith_short_12","alias_value":"FGW7ZZD2PIFW","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FGW7ZZD2PIFWM2AM","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FGW7ZZD2","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FGW7ZZD2PIFWM2AMHNK7HWX7HY","target":"record","payload":{"canonical_record":{"source":{"id":"1411.4389","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-17T08:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"cee88a093cf6888a0e030bcce3d8bb67bce07045037d2cb1e520aa6b1ecd8451","abstract_canon_sha256":"d9dfa9ef27e263d585432d346c4c46ca9e708849f33ea963eaef052dcebaccfd"},"schema_version":"1.0"},"canonical_sha256":"29adfce47a7a0b66680c3b55f3daff3e1cbe95d81106e50ac9ddd2eb242f6aff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:09.810063Z","signature_b64":"dqxWnKGvWduNpfdnyz7furWpnoTCszsST2TbXqUxLQHrDEgGk06irFLAqMMt9HEr5Udgcb30YWtoNP29bT6zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29adfce47a7a0b66680c3b55f3daff3e1cbe95d81106e50ac9ddd2eb242f6aff","last_reissued_at":"2026-05-18T01:13:09.809603Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:09.809603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1411.4389","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:13:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgDPt2rEoOk2BoL6LnBoqqdHAKzAmwd8HpnhYNuJddq9KSSFcxD5hh7MJTcxpZWELPmpjCuHbqY8fm7iHsJSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T00:02:37.650105Z"},"content_sha256":"376cff1964f5dad185f992e7144a99b0d6b3c242e646a2c596cd066301a701af","schema_version":"1.0","event_id":"sha256:376cff1964f5dad185f992e7144a99b0d6b3c242e646a2c596cd066301a701af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FGW7ZZD2PIFWM2AMHNK7HWX7HY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Kate Saenko, Lisa Anne Hendricks, Marcus Rohrbach, Sergio Guadarrama, Subhashini Venugopalan, Trevor Darrell","submitted_at":"2014-11-17T08:25:17Z","abstract_excerpt":"Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or \"temporally deep\", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.4389","kind":"arxiv","version":4},"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":"2026-05-18T01:13:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rh/kcdAwxUmwX81Xf02Wz5b3NOeG2KUmkpDqdg9K8CkrnTDu/yegI3i5zuZ2b/K3NYwHZpUoRJaCFLsG/gsTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T00:02:37.650572Z"},"content_sha256":"74bb7b9db810189aef87aa90f1743b5a3e2deefa2648f0a9d383459d5c02f891","schema_version":"1.0","event_id":"sha256:74bb7b9db810189aef87aa90f1743b5a3e2deefa2648f0a9d383459d5c02f891"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGW7ZZD2PIFWM2AMHNK7HWX7HY/bundle.json","state_url":"https://pith.science/pith/FGW7ZZD2PIFWM2AMHNK7HWX7HY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGW7ZZD2PIFWM2AMHNK7HWX7HY/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":"2026-05-20T00:02:37Z","links":{"resolver":"https://pith.science/pith/FGW7ZZD2PIFWM2AMHNK7HWX7HY","bundle":"https://pith.science/pith/FGW7ZZD2PIFWM2AMHNK7HWX7HY/bundle.json","state":"https://pith.science/pith/FGW7ZZD2PIFWM2AMHNK7HWX7HY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGW7ZZD2PIFWM2AMHNK7HWX7HY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FGW7ZZD2PIFWM2AMHNK7HWX7HY","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":"d9dfa9ef27e263d585432d346c4c46ca9e708849f33ea963eaef052dcebaccfd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-17T08:25:17Z","title_canon_sha256":"cee88a093cf6888a0e030bcce3d8bb67bce07045037d2cb1e520aa6b1ecd8451"},"schema_version":"1.0","source":{"id":"1411.4389","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.4389","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"arxiv_version","alias_value":"1411.4389v4","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.4389","created_at":"2026-05-18T01:13:09Z"},{"alias_kind":"pith_short_12","alias_value":"FGW7ZZD2PIFW","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FGW7ZZD2PIFWM2AM","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FGW7ZZD2","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:74bb7b9db810189aef87aa90f1743b5a3e2deefa2648f0a9d383459d5c02f891","target":"graph","created_at":"2026-05-18T01:13:09Z","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":"Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or \"temporally deep\", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive fi","authors_text":"Jeff Donahue, Kate Saenko, Lisa Anne Hendricks, Marcus Rohrbach, Sergio Guadarrama, Subhashini Venugopalan, Trevor Darrell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-17T08:25:17Z","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.4389","kind":"arxiv","version":4},"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":"sha256:376cff1964f5dad185f992e7144a99b0d6b3c242e646a2c596cd066301a701af","target":"record","created_at":"2026-05-18T01:13:09Z","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":"d9dfa9ef27e263d585432d346c4c46ca9e708849f33ea963eaef052dcebaccfd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-17T08:25:17Z","title_canon_sha256":"cee88a093cf6888a0e030bcce3d8bb67bce07045037d2cb1e520aa6b1ecd8451"},"schema_version":"1.0","source":{"id":"1411.4389","kind":"arxiv","version":4}},"canonical_sha256":"29adfce47a7a0b66680c3b55f3daff3e1cbe95d81106e50ac9ddd2eb242f6aff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29adfce47a7a0b66680c3b55f3daff3e1cbe95d81106e50ac9ddd2eb242f6aff","first_computed_at":"2026-05-18T01:13:09.809603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:09.809603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dqxWnKGvWduNpfdnyz7furWpnoTCszsST2TbXqUxLQHrDEgGk06irFLAqMMt9HEr5Udgcb30YWtoNP29bT6zBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:09.810063Z","signed_message":"canonical_sha256_bytes"},"source_id":"1411.4389","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:376cff1964f5dad185f992e7144a99b0d6b3c242e646a2c596cd066301a701af","sha256:74bb7b9db810189aef87aa90f1743b5a3e2deefa2648f0a9d383459d5c02f891"],"state_sha256":"373a601adb1e28bb54de4500fe7d063878c9c6bccbd9c7357eabfa81c78e79f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nm9K9HwrUuYoXc+++9bsE1xxHIzUrGdaFHowulwUG4rsaGRS3pFv3NGWjaferafzZ2YTjBJ2ckZ47bHFPx3oDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T00:02:37.653814Z","bundle_sha256":"cb99cd4f8933e9999c22f983fe63f7b17ee5e7d95d041a4dd2755c2a5cca7ea8"}}