{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2IFDILJDXNUKL2JWJZATMJAIDP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f59d5be1a73feb847de55caddf594950d7559a285b95a04ed00066219f3cedb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T17:28:09Z","title_canon_sha256":"b3b69c2ce3852814323301640dba63fe86cd5b817601dfe7ddd338e90621db67"},"schema_version":"1.0","source":{"id":"2312.14055","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14055","created_at":"2026-07-05T08:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14055v2","created_at":"2026-07-05T08:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14055","created_at":"2026-07-05T08:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"2IFDILJDXNUK","created_at":"2026-07-05T08:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"2IFDILJDXNUKL2JW","created_at":"2026-07-05T08:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"2IFDILJD","created_at":"2026-07-05T08:46:20Z"}],"graph_snapshots":[{"event_id":"sha256:db75c55c5f71928db750d2ebade4b8fc414a3292640210f9205c014820207231","target":"graph","created_at":"2026-07-05T08:46:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.14055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we aim to establish an automatic, scalable pipeline for denoising the large-scale instructional dataset and construct a high-quality video-text dataset with multiple descriptive steps supervision, named HowToStep. We make the following contributions: (i) improving the quality of sentences in dataset by upgrading ASR systems to reduce errors from speech recognition and prompting a large language model to transform noisy ASR transcripts into descriptive steps; (ii) proposing a Transformer-based architecture with all texts as queries, iteratively attending to the visual features, t","authors_text":"Qirui Chen, Tengda Han, Weidi Xie, Yanfeng Wang, Ya Zhang, Zeqian Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T17:28:09Z","title":"Multi-Sentence Grounding for Long-term Instructional Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14055","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2125ca5d18f98f31a0190954ce6d014910fd1f2f8e21ff9fb9bbf96a00fd9dd9","target":"record","created_at":"2026-07-05T08:46:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f59d5be1a73feb847de55caddf594950d7559a285b95a04ed00066219f3cedb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T17:28:09Z","title_canon_sha256":"b3b69c2ce3852814323301640dba63fe86cd5b817601dfe7ddd338e90621db67"},"schema_version":"1.0","source":{"id":"2312.14055","kind":"arxiv","version":2}},"canonical_sha256":"d20a342d23bb68a5e9364e413624081bdecb79b10b206410977b8dcb54a1a274","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d20a342d23bb68a5e9364e413624081bdecb79b10b206410977b8dcb54a1a274","first_computed_at":"2026-07-05T08:46:20.434614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:20.434614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d4mY569PCeJeqbAWSug8XgGevKj5oib/4OEH3aXClTboANsLyysgD6HH/hpMjMTDCMQECn4xoQhN63PW5K5wDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:20.435011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14055","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2125ca5d18f98f31a0190954ce6d014910fd1f2f8e21ff9fb9bbf96a00fd9dd9","sha256:db75c55c5f71928db750d2ebade4b8fc414a3292640210f9205c014820207231"],"state_sha256":"10bf01edf87a105099bc08d267a13bcfac3433fdb7ce7a4dccff483ed1732e63"}