{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EE7SJRG5PTNDSD7UJRG4ETRMUY","short_pith_number":"pith:EE7SJRG5","schema_version":"1.0","canonical_sha256":"213f24c4dd7cda390ff44c4dc24e2ca639c47c56fd58106e14d0254925b2c368","source":{"kind":"arxiv","id":"1907.12022","version":2},"attestation_state":"computed","paper":{"title":"DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Karthik Ramani, Min Liu, Zongyue Zhao","submitted_at":"2019-07-28T06:23:19Z","abstract_excerpt":"Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis. In this paper, we propose DAR-Net, a novel network architecture that focuses on dynamic feature aggregation. The central idea of DAR-Net is generating a self-adaptive pooling skeleton that considers both scene complexity and local geometry features. Providing variable semi-local receptive fields and weights, the skeleton serves as a bridge that connect local convolutional feature extractors and a global recurrent feature integrator. Experimental results on indoor scene datasets show advant"},"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":"1907.12022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-28T06:23:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b51160ea42e1dd08a7737aaa530f6ea3382b05292a1256aa194510ce492f0029","abstract_canon_sha256":"0f2f84efb51334226bb06cfee9cff58dcc4f3a851f2257dc8560b31a6c4200c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:23.504963Z","signature_b64":"kSjsGBU6TEtKtLHKviL/BN2rWujWmXl2wyGzsSsPB48S7QuTl2WP0ORPUsKKQXMSJApUIMZW2cfXO4F2+Jw0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213f24c4dd7cda390ff44c4dc24e2ca639c47c56fd58106e14d0254925b2c368","last_reissued_at":"2026-07-05T00:28:23.504554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:23.504554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Karthik Ramani, Min Liu, Zongyue Zhao","submitted_at":"2019-07-28T06:23:19Z","abstract_excerpt":"Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis. In this paper, we propose DAR-Net, a novel network architecture that focuses on dynamic feature aggregation. The central idea of DAR-Net is generating a self-adaptive pooling skeleton that considers both scene complexity and local geometry features. Providing variable semi-local receptive fields and weights, the skeleton serves as a bridge that connect local convolutional feature extractors and a global recurrent feature integrator. Experimental results on indoor scene datasets show advant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12022","kind":"arxiv","version":2},"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/1907.12022/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":"1907.12022","created_at":"2026-07-05T00:28:23.504612+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.12022v2","created_at":"2026-07-05T00:28:23.504612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12022","created_at":"2026-07-05T00:28:23.504612+00:00"},{"alias_kind":"pith_short_12","alias_value":"EE7SJRG5PTND","created_at":"2026-07-05T00:28:23.504612+00:00"},{"alias_kind":"pith_short_16","alias_value":"EE7SJRG5PTNDSD7U","created_at":"2026-07-05T00:28:23.504612+00:00"},{"alias_kind":"pith_short_8","alias_value":"EE7SJRG5","created_at":"2026-07-05T00:28:23.504612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":274,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY","json":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY.json","graph_json":"https://pith.science/api/pith-number/EE7SJRG5PTNDSD7UJRG4ETRMUY/graph.json","events_json":"https://pith.science/api/pith-number/EE7SJRG5PTNDSD7UJRG4ETRMUY/events.json","paper":"https://pith.science/paper/EE7SJRG5"},"agent_actions":{"view_html":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY","download_json":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY.json","view_paper":"https://pith.science/paper/EE7SJRG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.12022&json=true","fetch_graph":"https://pith.science/api/pith-number/EE7SJRG5PTNDSD7UJRG4ETRMUY/graph.json","fetch_events":"https://pith.science/api/pith-number/EE7SJRG5PTNDSD7UJRG4ETRMUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY/action/storage_attestation","attest_author":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY/action/author_attestation","sign_citation":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY/action/citation_signature","submit_replication":"https://pith.science/pith/EE7SJRG5PTNDSD7UJRG4ETRMUY/action/replication_record"}},"created_at":"2026-07-05T00:28:23.504612+00:00","updated_at":"2026-07-05T00:28:23.504612+00:00"}