{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JEA6UVDRKQW2BYOZOFL3YSYKY7","short_pith_number":"pith:JEA6UVDR","canonical_record":{"source":{"id":"2410.00436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-01T06:35:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"57c1305c12c95bcf202861e80c97476572900c0ec1d9677fa98c3785653dd45e","abstract_canon_sha256":"e367980eb959529676519f67ff18781d5634493cc6caac50c6d3510f8106460e"},"schema_version":"1.0"},"canonical_sha256":"4901ea5471542da0e1d97157bc4b0ac7e612a8140c503ab9ff9ab58c3bb7aed7","source":{"kind":"arxiv","id":"2410.00436","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00436","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00436v1","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00436","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"JEA6UVDRKQW2","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"JEA6UVDRKQW2BYOZ","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"JEA6UVDR","created_at":"2026-07-05T09:14:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JEA6UVDRKQW2BYOZOFL3YSYKY7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-01T06:35:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"57c1305c12c95bcf202861e80c97476572900c0ec1d9677fa98c3785653dd45e","abstract_canon_sha256":"e367980eb959529676519f67ff18781d5634493cc6caac50c6d3510f8106460e"},"schema_version":"1.0"},"canonical_sha256":"4901ea5471542da0e1d97157bc4b0ac7e612a8140c503ab9ff9ab58c3bb7aed7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:04.912639Z","signature_b64":"2fkHstw+IDmU3TJ4nHZk2+EsofM6pwn/am0dcJzQ1FXZmWT55ZNb9BQKpZFMJPPh9tTyxiA22iX5tbKdH290Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4901ea5471542da0e1d97157bc4b0ac7e612a8140c503ab9ff9ab58c3bb7aed7","last_reissued_at":"2026-07-05T09:14:04.912156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:04.912156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00436","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZHjehMHM52/ODEHxPDz/OeTshFjnupl2uqfxbcU3MuKQoi92RI+0EbFAbefcFZ75agHc0PhT9GvB3/4JtskBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:26:43.420493Z"},"content_sha256":"f3e5ed47cb13ff3a3154d419db80d80b5d439c4658f630accaa2442b8bcdf4a8","schema_version":"1.0","event_id":"sha256:f3e5ed47cb13ff3a3154d419db80d80b5d439c4658f630accaa2442b8bcdf4a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JEA6UVDRKQW2BYOZOFL3YSYKY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Daichi Saito, Komei Sugiura, Miyu Goko, Motonari Kambara, Seitaro Otsuki","submitted_at":"2024-10-01T06:35:34Z","abstract_excerpt":"In this study, we consider the problem of predicting task success for open-vocabulary manipulation by a manipulator, based on instruction sentences and egocentric images before and after manipulation. Conventional approaches, including multimodal large language models (MLLMs), often fail to appropriately understand detailed characteristics of objects and/or subtle changes in the position of objects. We propose Contrastive $\\lambda$-Repformer, which predicts task success for table-top manipulation tasks by aligning images with instruction sentences. Our method integrates the following three key"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00436","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/2410.00436/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6eVyj1MisHXL0p+eD9s4ZJww+M8w2tGB7bdPx0yqtwdL1iB2l15cVl+1MY0+WSeXGpxljU9P0LlSFbzyf/uDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:26:43.421049Z"},"content_sha256":"5170ee2dbad5e899692f70c172110b89ea6fb04c03eaf7e99c334f1ca761795d","schema_version":"1.0","event_id":"sha256:5170ee2dbad5e899692f70c172110b89ea6fb04c03eaf7e99c334f1ca761795d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEA6UVDRKQW2BYOZOFL3YSYKY7/bundle.json","state_url":"https://pith.science/pith/JEA6UVDRKQW2BYOZOFL3YSYKY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEA6UVDRKQW2BYOZOFL3YSYKY7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T01:26:43Z","links":{"resolver":"https://pith.science/pith/JEA6UVDRKQW2BYOZOFL3YSYKY7","bundle":"https://pith.science/pith/JEA6UVDRKQW2BYOZOFL3YSYKY7/bundle.json","state":"https://pith.science/pith/JEA6UVDRKQW2BYOZOFL3YSYKY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEA6UVDRKQW2BYOZOFL3YSYKY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JEA6UVDRKQW2BYOZOFL3YSYKY7","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":"e367980eb959529676519f67ff18781d5634493cc6caac50c6d3510f8106460e","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-01T06:35:34Z","title_canon_sha256":"57c1305c12c95bcf202861e80c97476572900c0ec1d9677fa98c3785653dd45e"},"schema_version":"1.0","source":{"id":"2410.00436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00436","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00436v1","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00436","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"JEA6UVDRKQW2","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"JEA6UVDRKQW2BYOZ","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"JEA6UVDR","created_at":"2026-07-05T09:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:5170ee2dbad5e899692f70c172110b89ea6fb04c03eaf7e99c334f1ca761795d","target":"graph","created_at":"2026-07-05T09:14:04Z","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/2410.00436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we consider the problem of predicting task success for open-vocabulary manipulation by a manipulator, based on instruction sentences and egocentric images before and after manipulation. Conventional approaches, including multimodal large language models (MLLMs), often fail to appropriately understand detailed characteristics of objects and/or subtle changes in the position of objects. We propose Contrastive $\\lambda$-Repformer, which predicts task success for table-top manipulation tasks by aligning images with instruction sentences. Our method integrates the following three key","authors_text":"Daichi Saito, Komei Sugiura, Miyu Goko, Motonari Kambara, Seitaro Otsuki","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-01T06:35:34Z","title":"Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00436","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:f3e5ed47cb13ff3a3154d419db80d80b5d439c4658f630accaa2442b8bcdf4a8","target":"record","created_at":"2026-07-05T09:14:04Z","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":"e367980eb959529676519f67ff18781d5634493cc6caac50c6d3510f8106460e","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-01T06:35:34Z","title_canon_sha256":"57c1305c12c95bcf202861e80c97476572900c0ec1d9677fa98c3785653dd45e"},"schema_version":"1.0","source":{"id":"2410.00436","kind":"arxiv","version":1}},"canonical_sha256":"4901ea5471542da0e1d97157bc4b0ac7e612a8140c503ab9ff9ab58c3bb7aed7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4901ea5471542da0e1d97157bc4b0ac7e612a8140c503ab9ff9ab58c3bb7aed7","first_computed_at":"2026-07-05T09:14:04.912156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:04.912156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2fkHstw+IDmU3TJ4nHZk2+EsofM6pwn/am0dcJzQ1FXZmWT55ZNb9BQKpZFMJPPh9tTyxiA22iX5tbKdH290Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:04.912639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3e5ed47cb13ff3a3154d419db80d80b5d439c4658f630accaa2442b8bcdf4a8","sha256:5170ee2dbad5e899692f70c172110b89ea6fb04c03eaf7e99c334f1ca761795d"],"state_sha256":"46dabed9a6c20303893c59e5c066c092782384c64e2ed657d5992dbe88925d87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wT77b0QJlpWsWHnGgxBJd+y7TuSLTXUW9V5MIpDOW/6hEcFqVIJbNxH6SJrj3sgRgAEPHaeqLo2tRKCsF+UHAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T01:26:43.424824Z","bundle_sha256":"9417e4498e480e3dd49bf0d9559b2bde081b972d18a511fb2343354023ca87af"}}