{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JWM3SKK52TZW7L4HV2ZXLQ4SRN","short_pith_number":"pith:JWM3SKK5","schema_version":"1.0","canonical_sha256":"4d99b9295dd4f36faf87aeb375c3928b50e3141ef44b23833d252d14983d1e64","source":{"kind":"arxiv","id":"1905.13209","version":4},"attestation_state":"computed","paper":{"title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo, Mingxing Tan","submitted_at":"2019-05-30T17:51:03Z","abstract_excerpt":"Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time dimension, using modules such as 3D convolutions, or by using two-stream design to capture both appearance and motion in videos. We interpret a video CNN as a collection of multi-stream convolutional blocks connected to each other, and propose the approach of automatically finding neural architectures with better connectivity and spatio-temporal interactions f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.13209","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T17:51:03Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"4ffe21c02bc477f80cbe9b6bf6e8c085ded476b21a3a58506ce95669aed8c908","abstract_canon_sha256":"45c328e09a5ba8a73b87794e68dcffcc8548e2f5a109a14c091f25120fe6bac9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:07.783593Z","signature_b64":"B4MHkBxCFHwa/7EB2CUbS1v4T6PS4M+8bsb8DZ/8sQ+8qa2bvcsfCQM7OfuWiyYfIigFF4i9xrnbx6cW1Vs2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d99b9295dd4f36faf87aeb375c3928b50e3141ef44b23833d252d14983d1e64","last_reissued_at":"2026-07-05T01:06:07.783166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:07.783166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo, Mingxing Tan","submitted_at":"2019-05-30T17:51:03Z","abstract_excerpt":"Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time dimension, using modules such as 3D convolutions, or by using two-stream design to capture both appearance and motion in videos. We interpret a video CNN as a collection of multi-stream convolutional blocks connected to each other, and propose the approach of automatically finding neural architectures with better connectivity and spatio-temporal interactions f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13209","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.13209/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.13209","created_at":"2026-07-05T01:06:07.783229+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13209v4","created_at":"2026-07-05T01:06:07.783229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13209","created_at":"2026-07-05T01:06:07.783229+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWM3SKK52TZW","created_at":"2026-07-05T01:06:07.783229+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWM3SKK52TZW7L4H","created_at":"2026-07-05T01:06:07.783229+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWM3SKK5","created_at":"2026-07-05T01:06:07.783229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06603","citing_title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN","json":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN.json","graph_json":"https://pith.science/api/pith-number/JWM3SKK52TZW7L4HV2ZXLQ4SRN/graph.json","events_json":"https://pith.science/api/pith-number/JWM3SKK52TZW7L4HV2ZXLQ4SRN/events.json","paper":"https://pith.science/paper/JWM3SKK5"},"agent_actions":{"view_html":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN","download_json":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN.json","view_paper":"https://pith.science/paper/JWM3SKK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13209&json=true","fetch_graph":"https://pith.science/api/pith-number/JWM3SKK52TZW7L4HV2ZXLQ4SRN/graph.json","fetch_events":"https://pith.science/api/pith-number/JWM3SKK52TZW7L4HV2ZXLQ4SRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN/action/storage_attestation","attest_author":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN/action/author_attestation","sign_citation":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN/action/citation_signature","submit_replication":"https://pith.science/pith/JWM3SKK52TZW7L4HV2ZXLQ4SRN/action/replication_record"}},"created_at":"2026-07-05T01:06:07.783229+00:00","updated_at":"2026-07-05T01:06:07.783229+00:00"}