{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:G5EFLRKVRD3XWT6MDB67TCXSXA","short_pith_number":"pith:G5EFLRKV","canonical_record":{"source":{"id":"1809.04288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T07:43:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5006b4d9175f3c568290fc62bf232e4db945ee912791d43f51cb44ded2cfa03b","abstract_canon_sha256":"8ea53739146ae97aa8f1e36af9395db645fa0e54c8612dbead3f4e2189dab251"},"schema_version":"1.0"},"canonical_sha256":"374855c55588f77b4fcc187df98af2b83cc2a8b8c192c0cc6efd6229cae45ef0","source":{"kind":"arxiv","id":"1809.04288","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04288","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04288v1","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04288","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"G5EFLRKVRD3X","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G5EFLRKVRD3XWT6M","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G5EFLRKV","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:G5EFLRKVRD3XWT6MDB67TCXSXA","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T07:43:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5006b4d9175f3c568290fc62bf232e4db945ee912791d43f51cb44ded2cfa03b","abstract_canon_sha256":"8ea53739146ae97aa8f1e36af9395db645fa0e54c8612dbead3f4e2189dab251"},"schema_version":"1.0"},"canonical_sha256":"374855c55588f77b4fcc187df98af2b83cc2a8b8c192c0cc6efd6229cae45ef0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:52.849951Z","signature_b64":"KSbdjSUcDRAjQerw6y+3K3+EDiMZhW5J54p2CLaEiQnturZ/s9EGpef+QlPhe8uAxCa1AZCjn2q2HEl05IqHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"374855c55588f77b4fcc187df98af2b83cc2a8b8c192c0cc6efd6229cae45ef0","last_reissued_at":"2026-05-18T00:05:52.849385Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:52.849385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04288","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":"2026-05-18T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bSY5y2GrFIEJobxiuOpFLKswOInqBXMeYxocYo3H2thXvwKzWgQuCd1yx6I7Fti1uQ4GbvOrvWkc3bDV0uiWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:59:33.200595Z"},"content_sha256":"625f0b9381f12cf088d75e1220267bde132bc117b118065707774a7fdfd28263","schema_version":"1.0","event_id":"sha256:625f0b9381f12cf088d75e1220267bde132bc117b118065707774a7fdfd28263"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:G5EFLRKVRD3XWT6MDB67TCXSXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Koichi Shinoda, Nobuyuki Shimizu, Takashi Miyazaki, Thao Minh Le","submitted_at":"2018-09-12T07:43:23Z","abstract_excerpt":"With the widespread use of intelligent systems, such as smart speakers, addressee recognition has become a concern in human-computer interaction, as more and more people expect such systems to understand complicated social scenes, including those outdoors, in cafeterias, and hospitals. Because previous studies typically focused only on pre-specified tasks with limited conversational situations such as controlling smart homes, we created a mock dataset called Addressee Recognition in Visual Scenes with Utterances (ARVSU) that contains a vast body of image variations in visual scenes with an ann"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04288","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":""},"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":"2026-05-18T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qhroj1nUpm7FQWHVqn7yjCBENROexbqX0VNDsh1tkxX34j3CT8PdyX/eqh9WBJH1ov8rVKHClSh6VZ1AC0urCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:59:33.200960Z"},"content_sha256":"b138badc36c2aee8b7420ffa8a89a3461d6cb028baec1fc4ea726d3973abcdf5","schema_version":"1.0","event_id":"sha256:b138badc36c2aee8b7420ffa8a89a3461d6cb028baec1fc4ea726d3973abcdf5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5EFLRKVRD3XWT6MDB67TCXSXA/bundle.json","state_url":"https://pith.science/pith/G5EFLRKVRD3XWT6MDB67TCXSXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5EFLRKVRD3XWT6MDB67TCXSXA/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":"2026-06-04T21:59:33Z","links":{"resolver":"https://pith.science/pith/G5EFLRKVRD3XWT6MDB67TCXSXA","bundle":"https://pith.science/pith/G5EFLRKVRD3XWT6MDB67TCXSXA/bundle.json","state":"https://pith.science/pith/G5EFLRKVRD3XWT6MDB67TCXSXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5EFLRKVRD3XWT6MDB67TCXSXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:G5EFLRKVRD3XWT6MDB67TCXSXA","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":"8ea53739146ae97aa8f1e36af9395db645fa0e54c8612dbead3f4e2189dab251","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T07:43:23Z","title_canon_sha256":"5006b4d9175f3c568290fc62bf232e4db945ee912791d43f51cb44ded2cfa03b"},"schema_version":"1.0","source":{"id":"1809.04288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04288","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04288v1","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04288","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"G5EFLRKVRD3X","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G5EFLRKVRD3XWT6M","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G5EFLRKV","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:b138badc36c2aee8b7420ffa8a89a3461d6cb028baec1fc4ea726d3973abcdf5","target":"graph","created_at":"2026-05-18T00:05:52Z","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"},"paper":{"abstract_excerpt":"With the widespread use of intelligent systems, such as smart speakers, addressee recognition has become a concern in human-computer interaction, as more and more people expect such systems to understand complicated social scenes, including those outdoors, in cafeterias, and hospitals. Because previous studies typically focused only on pre-specified tasks with limited conversational situations such as controlling smart homes, we created a mock dataset called Addressee Recognition in Visual Scenes with Utterances (ARVSU) that contains a vast body of image variations in visual scenes with an ann","authors_text":"Koichi Shinoda, Nobuyuki Shimizu, Takashi Miyazaki, Thao Minh Le","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T07:43:23Z","title":"Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04288","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":"sha256:625f0b9381f12cf088d75e1220267bde132bc117b118065707774a7fdfd28263","target":"record","created_at":"2026-05-18T00:05:52Z","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":"8ea53739146ae97aa8f1e36af9395db645fa0e54c8612dbead3f4e2189dab251","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-12T07:43:23Z","title_canon_sha256":"5006b4d9175f3c568290fc62bf232e4db945ee912791d43f51cb44ded2cfa03b"},"schema_version":"1.0","source":{"id":"1809.04288","kind":"arxiv","version":1}},"canonical_sha256":"374855c55588f77b4fcc187df98af2b83cc2a8b8c192c0cc6efd6229cae45ef0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"374855c55588f77b4fcc187df98af2b83cc2a8b8c192c0cc6efd6229cae45ef0","first_computed_at":"2026-05-18T00:05:52.849385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:52.849385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KSbdjSUcDRAjQerw6y+3K3+EDiMZhW5J54p2CLaEiQnturZ/s9EGpef+QlPhe8uAxCa1AZCjn2q2HEl05IqHBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:52.849951Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:625f0b9381f12cf088d75e1220267bde132bc117b118065707774a7fdfd28263","sha256:b138badc36c2aee8b7420ffa8a89a3461d6cb028baec1fc4ea726d3973abcdf5"],"state_sha256":"33d9b60331ac71ea91f5a4739a1da7682115b266f805356d24ca2cd189e4a64e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BDKTSsbrAstkAPI/fSGMRJmZeH6RQTYKKHxKyk85Hhu0YcxK8G/deEJP7V6dlaFNluFPpyVs0IJ2rqMnL+4tBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T21:59:33.206413Z","bundle_sha256":"dddcdab924c1d3fe9b6df4cee55a35d8771d6e8517e6606d4c07b5213a14ed41"}}