{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KQ3WHAGPWZRFN7QNKS6ICP5AIL","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":"3149ff3d9e8337f0953c2cd31b18cc1b3c8e7ec14598a133e5e7504003ba16bc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-09T05:22:01Z","title_canon_sha256":"32fe300ba3fe0b2aa66623dcd1fdaf4177378bd0196eefe612ac7c7a61c583c7"},"schema_version":"1.0","source":{"id":"2101.05061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.05061","created_at":"2026-07-05T02:06:37Z"},{"alias_kind":"arxiv_version","alias_value":"2101.05061v1","created_at":"2026-07-05T02:06:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05061","created_at":"2026-07-05T02:06:37Z"},{"alias_kind":"pith_short_12","alias_value":"KQ3WHAGPWZRF","created_at":"2026-07-05T02:06:37Z"},{"alias_kind":"pith_short_16","alias_value":"KQ3WHAGPWZRFN7QN","created_at":"2026-07-05T02:06:37Z"},{"alias_kind":"pith_short_8","alias_value":"KQ3WHAGP","created_at":"2026-07-05T02:06:37Z"}],"graph_snapshots":[{"event_id":"sha256:e5e6783a16abfd768200efbaf4d38e66b3f0815b2cb172e67f7b9eba8c36a421","target":"graph","created_at":"2026-07-05T02:06:37Z","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/2101.05061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning actions from human demonstration video is promising for intelligent robotic systems. Extracting the exact section and re-observing the extracted video section in detail is important for imitating complex skills because human motions give valuable hints for robots. However, the general video understanding methods focus more on the understanding of the full frame,lacking consideration on extracting accurate sections and aligning them with the human's intent. We propose a Learning-from-Observation framework that splits and understands a video of a human demonstration with verbal instruct","authors_text":"Iori Yanokura, Katsushi Ikeuchi, Kazuhiro Sasabuchi, Masayuki Inaba, Naoki Wake","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-09T05:22:01Z","title":"Understanding Action Sequences based on Video Captioning for Learning-from-Observation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05061","kind":"arxiv","version":1},"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":"sha256:50c2ab7391569b5d27ccc59be69314ff4fd15564ca0902d3b6edc1d0cf232cdb","target":"record","created_at":"2026-07-05T02:06:37Z","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":"3149ff3d9e8337f0953c2cd31b18cc1b3c8e7ec14598a133e5e7504003ba16bc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-09T05:22:01Z","title_canon_sha256":"32fe300ba3fe0b2aa66623dcd1fdaf4177378bd0196eefe612ac7c7a61c583c7"},"schema_version":"1.0","source":{"id":"2101.05061","kind":"arxiv","version":1}},"canonical_sha256":"54376380cfb66256fe0d54bc813fa042d652159354da1c39548e5ac75848adfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54376380cfb66256fe0d54bc813fa042d652159354da1c39548e5ac75848adfb","first_computed_at":"2026-07-05T02:06:37.612292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:06:37.612292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5qbPL0cAFH8U6WhxLJVh7c6JxOvishpnA2urDN8nr50cRKMpd5/hzumfEz9w3e9HJqEO+xVCz6gATpVxNOiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:06:37.612823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.05061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50c2ab7391569b5d27ccc59be69314ff4fd15564ca0902d3b6edc1d0cf232cdb","sha256:e5e6783a16abfd768200efbaf4d38e66b3f0815b2cb172e67f7b9eba8c36a421"],"state_sha256":"ab4abf48e9f72ad249b9c2539edc701eaf2c17066941a9927d78749f240500af"}