{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FM7ZOENFHUJJVJ3W73AQW3DJ4F","short_pith_number":"pith:FM7ZOENF","canonical_record":{"source":{"id":"2003.04210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-09T15:49:01Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"88c0c9ae340be7e4d5dee71946a9816b354d5bcea6dd61a55a31d046287b3f0a","abstract_canon_sha256":"c3972e67da2e029f35304d164700fb5190c3988de0dd20ff6f80c58e41496943"},"schema_version":"1.0"},"canonical_sha256":"2b3f9711a53d129aa776fec10b6c69e1678c2c3aa2a6068451595f4967eb8456","source":{"kind":"arxiv","id":"2003.04210","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04210","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04210v1","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04210","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"FM7ZOENFHUJJ","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"FM7ZOENFHUJJVJ3W","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"FM7ZOENF","created_at":"2026-07-05T00:46:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FM7ZOENFHUJJVJ3W73AQW3DJ4F","target":"record","payload":{"canonical_record":{"source":{"id":"2003.04210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-09T15:49:01Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"88c0c9ae340be7e4d5dee71946a9816b354d5bcea6dd61a55a31d046287b3f0a","abstract_canon_sha256":"c3972e67da2e029f35304d164700fb5190c3988de0dd20ff6f80c58e41496943"},"schema_version":"1.0"},"canonical_sha256":"2b3f9711a53d129aa776fec10b6c69e1678c2c3aa2a6068451595f4967eb8456","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:46:40.729771Z","signature_b64":"AkpNXtOi4G4axAaVWEUgH8vPgg9fc3IKpyjbOdBpCXorH5qufRCGStBwBsqcIJUwDrpm2jmwwKWTAdRuvi7aCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b3f9711a53d129aa776fec10b6c69e1678c2c3aa2a6068451595f4967eb8456","last_reissued_at":"2026-07-05T00:46:40.729357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:46:40.729357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.04210","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":"2026-07-05T00:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HnsXjInCqrSC/IBAZI3rCSgLYRS84U4Aa4VKCO8Ou8LwdXhrU5wdwE2lz37lPLcWTFe2a2R6vnBM6hJSK1WzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:19:48.508589Z"},"content_sha256":"dbc2cde62d17015384fdd0caf7fa18051f915dad5d1201ccb7288a9ec10cbf0c","schema_version":"1.0","event_id":"sha256:dbc2cde62d17015384fdd0caf7fa18051f915dad5d1201ccb7288a9ec10cbf0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FM7ZOENFHUJJVJ3W73AQW3DJ4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool","submitted_at":"2020-03-09T15:49:01Z","abstract_excerpt":"Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic labelling of sound-making objects, purely based on binaural sounds. We propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a 360 degree camera. The co-existence of visual and audio cues is leveraged for supervision transfer. In particular, we employ a cross-modal distillation framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04210","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/2003.04210/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":"2026-07-05T00:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8/bROjYYnhAIpxA3OvLqM7DTNnGRQg8HoQdaqyD7+ccNtVegXSBYAsRfK9uV6wPGUYt6qvG2WWKptFDw/whxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:19:48.508970Z"},"content_sha256":"af14b51b7347dddf659972150c3cc1893e4f93af60f98d093579dcc624f64366","schema_version":"1.0","event_id":"sha256:af14b51b7347dddf659972150c3cc1893e4f93af60f98d093579dcc624f64366"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FM7ZOENFHUJJVJ3W73AQW3DJ4F/bundle.json","state_url":"https://pith.science/pith/FM7ZOENFHUJJVJ3W73AQW3DJ4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FM7ZOENFHUJJVJ3W73AQW3DJ4F/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":"2026-08-22T23:19:48Z","links":{"resolver":"https://pith.science/pith/FM7ZOENFHUJJVJ3W73AQW3DJ4F","bundle":"https://pith.science/pith/FM7ZOENFHUJJVJ3W73AQW3DJ4F/bundle.json","state":"https://pith.science/pith/FM7ZOENFHUJJVJ3W73AQW3DJ4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FM7ZOENFHUJJVJ3W73AQW3DJ4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FM7ZOENFHUJJVJ3W73AQW3DJ4F","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":"c3972e67da2e029f35304d164700fb5190c3988de0dd20ff6f80c58e41496943","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-09T15:49:01Z","title_canon_sha256":"88c0c9ae340be7e4d5dee71946a9816b354d5bcea6dd61a55a31d046287b3f0a"},"schema_version":"1.0","source":{"id":"2003.04210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04210","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04210v1","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04210","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"FM7ZOENFHUJJ","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"FM7ZOENFHUJJVJ3W","created_at":"2026-07-05T00:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"FM7ZOENF","created_at":"2026-07-05T00:46:40Z"}],"graph_snapshots":[{"event_id":"sha256:af14b51b7347dddf659972150c3cc1893e4f93af60f98d093579dcc624f64366","target":"graph","created_at":"2026-07-05T00:46:40Z","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/2003.04210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic labelling of sound-making objects, purely based on binaural sounds. We propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a 360 degree camera. The co-existence of visual and audio cues is leveraged for supervision transfer. In particular, we employ a cross-modal distillation framewo","authors_text":"Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-09T15:49:01Z","title":"Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04210","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:dbc2cde62d17015384fdd0caf7fa18051f915dad5d1201ccb7288a9ec10cbf0c","target":"record","created_at":"2026-07-05T00:46:40Z","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":"c3972e67da2e029f35304d164700fb5190c3988de0dd20ff6f80c58e41496943","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-09T15:49:01Z","title_canon_sha256":"88c0c9ae340be7e4d5dee71946a9816b354d5bcea6dd61a55a31d046287b3f0a"},"schema_version":"1.0","source":{"id":"2003.04210","kind":"arxiv","version":1}},"canonical_sha256":"2b3f9711a53d129aa776fec10b6c69e1678c2c3aa2a6068451595f4967eb8456","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b3f9711a53d129aa776fec10b6c69e1678c2c3aa2a6068451595f4967eb8456","first_computed_at":"2026-07-05T00:46:40.729357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:46:40.729357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AkpNXtOi4G4axAaVWEUgH8vPgg9fc3IKpyjbOdBpCXorH5qufRCGStBwBsqcIJUwDrpm2jmwwKWTAdRuvi7aCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:46:40.729771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.04210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbc2cde62d17015384fdd0caf7fa18051f915dad5d1201ccb7288a9ec10cbf0c","sha256:af14b51b7347dddf659972150c3cc1893e4f93af60f98d093579dcc624f64366"],"state_sha256":"320983c6d8bcf3f9bb060075fe37637db68edc2889a0680911438e0401d4e52f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02bDQNDnGnh5wn42j1+cgEXpBqtdS5eYONSW0ozZeiiC9uz42uFjV91nrC2Eg5E5BEl1vBryetRjLxAxsx8EDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:19:48.511491Z","bundle_sha256":"7db382fac04ad9c331eecc6eb76403b40d66c7c02ddb47df42ef547439335993"}}