{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QM6WRZVTS7K4EQF7L4ENGCOJPC","short_pith_number":"pith:QM6WRZVT","schema_version":"1.0","canonical_sha256":"833d68e6b397d5c240bf5f08d309c978bedba873cb923b2eed2ea2058fa80961","source":{"kind":"arxiv","id":"2303.14676","version":3},"attestation_state":"computed","paper":{"title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanlin Wang, Limin Wang, Sheng Guo, Yilu Wu","submitted_at":"2023-03-26T10:50:16Z","abstract_excerpt":"In this paper, we study the problem of procedure planning in instructional videos, which aims to make a plan (i.e. a sequence of actions) given the current visual observation and the desired goal. Previous works cast this as a sequence modeling problem and leverage either intermediate visual observations or language instructions as supervision to make autoregressive planning, resulting in complex learning schemes and expensive annotation costs. To avoid intermediate supervision annotation and error accumulation caused by planning autoregressively, we propose a diffusion-based framework, coined"},"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":"2303.14676","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-26T10:50:16Z","cross_cats_sorted":[],"title_canon_sha256":"1993bc320a4fd72d499618e5204e824d00cd8b2fb49837c68f05522915892061","abstract_canon_sha256":"4a8d2ff50c2cf4f1e9760ff85a7b45f1ed17af0a88445b830d8226e50367be56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:38.719385Z","signature_b64":"peAuHPWSP9X6K5a2kHN+WmsquuvWQit5R5GKBX8ouR74PwzqMm9hd3zz7w0tIEGRrLsSmEZ7PZaTgxLnxUFrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"833d68e6b397d5c240bf5f08d309c978bedba873cb923b2eed2ea2058fa80961","last_reissued_at":"2026-07-05T10:03:38.718889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:38.718889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanlin Wang, Limin Wang, Sheng Guo, Yilu Wu","submitted_at":"2023-03-26T10:50:16Z","abstract_excerpt":"In this paper, we study the problem of procedure planning in instructional videos, which aims to make a plan (i.e. a sequence of actions) given the current visual observation and the desired goal. Previous works cast this as a sequence modeling problem and leverage either intermediate visual observations or language instructions as supervision to make autoregressive planning, resulting in complex learning schemes and expensive annotation costs. To avoid intermediate supervision annotation and error accumulation caused by planning autoregressively, we propose a diffusion-based framework, coined"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14676","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.14676/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":"2303.14676","created_at":"2026-07-05T10:03:38.718952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14676v3","created_at":"2026-07-05T10:03:38.718952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14676","created_at":"2026-07-05T10:03:38.718952+00:00"},{"alias_kind":"pith_short_12","alias_value":"QM6WRZVTS7K4","created_at":"2026-07-05T10:03:38.718952+00:00"},{"alias_kind":"pith_short_16","alias_value":"QM6WRZVTS7K4EQF7","created_at":"2026-07-05T10:03:38.718952+00:00"},{"alias_kind":"pith_short_8","alias_value":"QM6WRZVT","created_at":"2026-07-05T10:03:38.718952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13821","citing_title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC","json":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC.json","graph_json":"https://pith.science/api/pith-number/QM6WRZVTS7K4EQF7L4ENGCOJPC/graph.json","events_json":"https://pith.science/api/pith-number/QM6WRZVTS7K4EQF7L4ENGCOJPC/events.json","paper":"https://pith.science/paper/QM6WRZVT"},"agent_actions":{"view_html":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC","download_json":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC.json","view_paper":"https://pith.science/paper/QM6WRZVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14676&json=true","fetch_graph":"https://pith.science/api/pith-number/QM6WRZVTS7K4EQF7L4ENGCOJPC/graph.json","fetch_events":"https://pith.science/api/pith-number/QM6WRZVTS7K4EQF7L4ENGCOJPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC/action/storage_attestation","attest_author":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC/action/author_attestation","sign_citation":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC/action/citation_signature","submit_replication":"https://pith.science/pith/QM6WRZVTS7K4EQF7L4ENGCOJPC/action/replication_record"}},"created_at":"2026-07-05T10:03:38.718952+00:00","updated_at":"2026-07-05T10:03:38.718952+00:00"}