{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GETYR3QPNOOR3WGYTJAMNXAYXL","short_pith_number":"pith:GETYR3QP","schema_version":"1.0","canonical_sha256":"312788ee0f6b9d1dd8d89a40c6dc18bacae76573cf0dd2b8ade64fa31e47497c","source":{"kind":"arxiv","id":"2112.11547","version":1},"attestation_state":"computed","paper":{"title":"Decompose the Sounds and Pixels, Recompose the Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Haoda Li, Juwei Lu, Md Ibrahim Khalil, Peng Dai, Varshanth R. Rao","submitted_at":"2021-12-21T22:22:46Z","abstract_excerpt":"In this paper, we propose a framework centering around a novel architecture called the Event Decomposition Recomposition Network (EDRNet) to tackle the Audio-Visual Event (AVE) localization problem in the supervised and weakly supervised settings. AVEs in the real world exhibit common unravelling patterns (termed as Event Progress Checkpoints (EPC)), which humans can perceive through the cooperation of their auditory and visual senses. Unlike earlier methods which attempt to recognize entire event sequences, the EDRNet models EPCs and inter-EPC relationships using stacked temporal convolutions"},"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":"2112.11547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-21T22:22:46Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"2bef2e47709836aae84a9b824f85d5678c62725755d7da794125e0665a2484a4","abstract_canon_sha256":"5d6e1c5c8e7f64221c5d7376eec4dcc62eabe21117c9dd349c105ecd50d340d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:08.158606Z","signature_b64":"jC91/r9Q+gFA1cBczbyYH43tn5MCrTNk2CYzApKa4LRu9nSr3FYBkacOtu8zRvV9y4LBqa2kURkLimln+bZFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"312788ee0f6b9d1dd8d89a40c6dc18bacae76573cf0dd2b8ade64fa31e47497c","last_reissued_at":"2026-07-05T03:43:08.158240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:08.158240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decompose the Sounds and Pixels, Recompose the Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Haoda Li, Juwei Lu, Md Ibrahim Khalil, Peng Dai, Varshanth R. Rao","submitted_at":"2021-12-21T22:22:46Z","abstract_excerpt":"In this paper, we propose a framework centering around a novel architecture called the Event Decomposition Recomposition Network (EDRNet) to tackle the Audio-Visual Event (AVE) localization problem in the supervised and weakly supervised settings. AVEs in the real world exhibit common unravelling patterns (termed as Event Progress Checkpoints (EPC)), which humans can perceive through the cooperation of their auditory and visual senses. Unlike earlier methods which attempt to recognize entire event sequences, the EDRNet models EPCs and inter-EPC relationships using stacked temporal convolutions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11547","kind":"arxiv","version":1},"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/2112.11547/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":"2112.11547","created_at":"2026-07-05T03:43:08.158294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11547v1","created_at":"2026-07-05T03:43:08.158294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11547","created_at":"2026-07-05T03:43:08.158294+00:00"},{"alias_kind":"pith_short_12","alias_value":"GETYR3QPNOOR","created_at":"2026-07-05T03:43:08.158294+00:00"},{"alias_kind":"pith_short_16","alias_value":"GETYR3QPNOOR3WGY","created_at":"2026-07-05T03:43:08.158294+00:00"},{"alias_kind":"pith_short_8","alias_value":"GETYR3QP","created_at":"2026-07-05T03:43:08.158294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL","json":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL.json","graph_json":"https://pith.science/api/pith-number/GETYR3QPNOOR3WGYTJAMNXAYXL/graph.json","events_json":"https://pith.science/api/pith-number/GETYR3QPNOOR3WGYTJAMNXAYXL/events.json","paper":"https://pith.science/paper/GETYR3QP"},"agent_actions":{"view_html":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL","download_json":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL.json","view_paper":"https://pith.science/paper/GETYR3QP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11547&json=true","fetch_graph":"https://pith.science/api/pith-number/GETYR3QPNOOR3WGYTJAMNXAYXL/graph.json","fetch_events":"https://pith.science/api/pith-number/GETYR3QPNOOR3WGYTJAMNXAYXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL/action/storage_attestation","attest_author":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL/action/author_attestation","sign_citation":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL/action/citation_signature","submit_replication":"https://pith.science/pith/GETYR3QPNOOR3WGYTJAMNXAYXL/action/replication_record"}},"created_at":"2026-07-05T03:43:08.158294+00:00","updated_at":"2026-07-05T03:43:08.158294+00:00"}