{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:76IDXPSD5SEVMVX2X6PW7LGZUT","short_pith_number":"pith:76IDXPSD","canonical_record":{"source":{"id":"1511.05298","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-17T07:49:58Z","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"10dde40d3320f0a4bef70e3e5fd63aa6bdb95c44cafad1d81f455d82436b30a2","abstract_canon_sha256":"dac1d23c1ec5d5ba8740a07e9ec1d3ae2ef711f9672e5a63d0ab69a0f860cedb"},"schema_version":"1.0"},"canonical_sha256":"ff903bbe43ec895656fabf9f6facd9a4e698436ac1ad66b77923fd3fbeea5edc","source":{"kind":"arxiv","id":"1511.05298","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05298","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05298v3","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05298","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"76IDXPSD5SEV","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"76IDXPSD5SEVMVX2","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"76IDXPSD","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:76IDXPSD5SEVMVX2X6PW7LGZUT","target":"record","payload":{"canonical_record":{"source":{"id":"1511.05298","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-17T07:49:58Z","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"10dde40d3320f0a4bef70e3e5fd63aa6bdb95c44cafad1d81f455d82436b30a2","abstract_canon_sha256":"dac1d23c1ec5d5ba8740a07e9ec1d3ae2ef711f9672e5a63d0ab69a0f860cedb"},"schema_version":"1.0"},"canonical_sha256":"ff903bbe43ec895656fabf9f6facd9a4e698436ac1ad66b77923fd3fbeea5edc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:25.016677Z","signature_b64":"RrlQ3ZQoo/lRx//vrJSU8ZetHGeNRlqje1Q1xwaq0Jy+rZbRc8uH7+musbYve9kgXltKfbR4FZ8/BE6srbzhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff903bbe43ec895656fabf9f6facd9a4e698436ac1ad66b77923fd3fbeea5edc","last_reissued_at":"2026-05-18T01:17:25.016184Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:25.016184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.05298","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":"2026-05-18T01:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c1tn5eFiht2dR3DDOGHVW9hzTfKdXP9Qn2c2PFX6Ws2Ivfl+qdFsmprFPEHi/J6pDtXUf2ezdHbGWSEKmtVSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:06:36.367085Z"},"content_sha256":"f1fc44cd7d934cb8e04a3912b234983d4207315c51153eefa5657919cd97bcc1","schema_version":"1.0","event_id":"sha256:f1fc44cd7d934cb8e04a3912b234983d4207315c51153eefa5657919cd97bcc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:76IDXPSD5SEVMVX2X6PW7LGZUT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.CV","authors_text":"Amir R. Zamir, Ashesh Jain, Ashutosh Saxena, Silvio Savarese","submitted_at":"2015-11-17T07:49:58Z","abstract_excerpt":"Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level structure and can benefit from it. Spatio-temporal graphs are a popular tool for imposing such high-level intuitions in the formulation of real world problems. In this paper, we propose an approach for combining the power of high-level spatio-temporal graphs and sequence learning success of Recurrent Neural Networks~(RNNs). We develop a scalable method for cas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05298","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":"2026-05-18T01:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GcBxrWhVIS7ViO5RFCD4RJ6GmBn7wPyuZuyStzuZ6551Fzfd1p684IcKdyGTZv9m2pJBYvI4F+hHau45FIPtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:06:36.367832Z"},"content_sha256":"f7b851f3d1b58480e6fa570f3ec7eed7cbbed3aa27c4caa4499d453c8f48f3a9","schema_version":"1.0","event_id":"sha256:f7b851f3d1b58480e6fa570f3ec7eed7cbbed3aa27c4caa4499d453c8f48f3a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76IDXPSD5SEVMVX2X6PW7LGZUT/bundle.json","state_url":"https://pith.science/pith/76IDXPSD5SEVMVX2X6PW7LGZUT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76IDXPSD5SEVMVX2X6PW7LGZUT/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":"2026-06-06T11:06:36Z","links":{"resolver":"https://pith.science/pith/76IDXPSD5SEVMVX2X6PW7LGZUT","bundle":"https://pith.science/pith/76IDXPSD5SEVMVX2X6PW7LGZUT/bundle.json","state":"https://pith.science/pith/76IDXPSD5SEVMVX2X6PW7LGZUT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76IDXPSD5SEVMVX2X6PW7LGZUT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:76IDXPSD5SEVMVX2X6PW7LGZUT","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":"dac1d23c1ec5d5ba8740a07e9ec1d3ae2ef711f9672e5a63d0ab69a0f860cedb","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-17T07:49:58Z","title_canon_sha256":"10dde40d3320f0a4bef70e3e5fd63aa6bdb95c44cafad1d81f455d82436b30a2"},"schema_version":"1.0","source":{"id":"1511.05298","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05298","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05298v3","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05298","created_at":"2026-05-18T01:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"76IDXPSD5SEV","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"76IDXPSD5SEVMVX2","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"76IDXPSD","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:f7b851f3d1b58480e6fa570f3ec7eed7cbbed3aa27c4caa4499d453c8f48f3a9","target":"graph","created_at":"2026-05-18T01:17:25Z","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":"Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level structure and can benefit from it. Spatio-temporal graphs are a popular tool for imposing such high-level intuitions in the formulation of real world problems. In this paper, we propose an approach for combining the power of high-level spatio-temporal graphs and sequence learning success of Recurrent Neural Networks~(RNNs). We develop a scalable method for cas","authors_text":"Amir R. Zamir, Ashesh Jain, Ashutosh Saxena, Silvio Savarese","cross_cats":["cs.LG","cs.NE","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-17T07:49:58Z","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05298","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:f1fc44cd7d934cb8e04a3912b234983d4207315c51153eefa5657919cd97bcc1","target":"record","created_at":"2026-05-18T01:17:25Z","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":"dac1d23c1ec5d5ba8740a07e9ec1d3ae2ef711f9672e5a63d0ab69a0f860cedb","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-17T07:49:58Z","title_canon_sha256":"10dde40d3320f0a4bef70e3e5fd63aa6bdb95c44cafad1d81f455d82436b30a2"},"schema_version":"1.0","source":{"id":"1511.05298","kind":"arxiv","version":3}},"canonical_sha256":"ff903bbe43ec895656fabf9f6facd9a4e698436ac1ad66b77923fd3fbeea5edc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff903bbe43ec895656fabf9f6facd9a4e698436ac1ad66b77923fd3fbeea5edc","first_computed_at":"2026-05-18T01:17:25.016184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:25.016184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RrlQ3ZQoo/lRx//vrJSU8ZetHGeNRlqje1Q1xwaq0Jy+rZbRc8uH7+musbYve9kgXltKfbR4FZ8/BE6srbzhDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:25.016677Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.05298","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1fc44cd7d934cb8e04a3912b234983d4207315c51153eefa5657919cd97bcc1","sha256:f7b851f3d1b58480e6fa570f3ec7eed7cbbed3aa27c4caa4499d453c8f48f3a9"],"state_sha256":"d26f356bfc05737da48575079412df419faded75682bf449e9d143309e5fd6cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YkZdyasAAD4G2Nx0Z2jBETDI4fBIH50Q5YRsSZIY4T6ak5twXAG3ImCryYehu2BTftvXdnEd/SzUZCPkr2pOBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T11:06:36.371534Z","bundle_sha256":"35dd2f014869f0a23ff6645f0066045ff645393c353bc46e2c3fc73eb694d03c"}}