{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4N35VNEOGCL6SJ4E35UW2LCEUG","short_pith_number":"pith:4N35VNEO","schema_version":"1.0","canonical_sha256":"e377dab48e3097e92784df696d2c44a1823305c1a6e6311e0d2d85d3fb6afd83","source":{"kind":"arxiv","id":"2507.03393","version":1},"attestation_state":"computed","paper":{"title":"Masked Temporal Interpolation 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":"Beichen Zhang, Junqi Jing, Lingshuai Lin, Shuhui Wang, Tingting Chai, Weigang Zhang, Yufan Zhou, Zhaobo Qi","submitted_at":"2025-07-04T08:54:59Z","abstract_excerpt":"In this paper, we address the challenge of procedure planning in instructional videos, aiming to generate coherent and task-aligned action sequences from start and end visual observations. Previous work has mainly relied on text-level supervision to bridge the gap between observed states and unobserved actions, but it struggles with capturing intricate temporal relationships among actions. Building on these efforts, we propose the Masked Temporal Interpolation Diffusion (MTID) model that introduces a latent space temporal interpolation module within the diffusion model. This module leverages a"},"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":"2507.03393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-04T08:54:59Z","cross_cats_sorted":[],"title_canon_sha256":"2e7f9c923841cf08ff6490d5582556c09d731def4d536107ec34cd7f5db56cd9","abstract_canon_sha256":"884fa928cd56d1840e95af95963df35f5e65f73d8068002d2e8e2685c4972c87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:58.799003Z","signature_b64":"1h5LihqZyHf0XeI7Y3B19RjiOo0PY76vZMNk9X6+WPHqkbPhtXuKMVD6iLlNpglr178ixaRd6B6s0blpEWnSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e377dab48e3097e92784df696d2c44a1823305c1a6e6311e0d2d85d3fb6afd83","last_reissued_at":"2026-07-05T11:31:58.798508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:58.798508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Temporal Interpolation 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":"Beichen Zhang, Junqi Jing, Lingshuai Lin, Shuhui Wang, Tingting Chai, Weigang Zhang, Yufan Zhou, Zhaobo Qi","submitted_at":"2025-07-04T08:54:59Z","abstract_excerpt":"In this paper, we address the challenge of procedure planning in instructional videos, aiming to generate coherent and task-aligned action sequences from start and end visual observations. Previous work has mainly relied on text-level supervision to bridge the gap between observed states and unobserved actions, but it struggles with capturing intricate temporal relationships among actions. Building on these efforts, we propose the Masked Temporal Interpolation Diffusion (MTID) model that introduces a latent space temporal interpolation module within the diffusion model. This module leverages a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03393","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/2507.03393/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":"2507.03393","created_at":"2026-07-05T11:31:58.798569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03393v1","created_at":"2026-07-05T11:31:58.798569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03393","created_at":"2026-07-05T11:31:58.798569+00:00"},{"alias_kind":"pith_short_12","alias_value":"4N35VNEOGCL6","created_at":"2026-07-05T11:31:58.798569+00:00"},{"alias_kind":"pith_short_16","alias_value":"4N35VNEOGCL6SJ4E","created_at":"2026-07-05T11:31:58.798569+00:00"},{"alias_kind":"pith_short_8","alias_value":"4N35VNEO","created_at":"2026-07-05T11:31:58.798569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.23058","citing_title":"GeoWorld: Geometric World Models","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG","json":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG.json","graph_json":"https://pith.science/api/pith-number/4N35VNEOGCL6SJ4E35UW2LCEUG/graph.json","events_json":"https://pith.science/api/pith-number/4N35VNEOGCL6SJ4E35UW2LCEUG/events.json","paper":"https://pith.science/paper/4N35VNEO"},"agent_actions":{"view_html":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG","download_json":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG.json","view_paper":"https://pith.science/paper/4N35VNEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03393&json=true","fetch_graph":"https://pith.science/api/pith-number/4N35VNEOGCL6SJ4E35UW2LCEUG/graph.json","fetch_events":"https://pith.science/api/pith-number/4N35VNEOGCL6SJ4E35UW2LCEUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG/action/storage_attestation","attest_author":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG/action/author_attestation","sign_citation":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG/action/citation_signature","submit_replication":"https://pith.science/pith/4N35VNEOGCL6SJ4E35UW2LCEUG/action/replication_record"}},"created_at":"2026-07-05T11:31:58.798569+00:00","updated_at":"2026-07-05T11:31:58.798569+00:00"}