{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5AXMADUIXBLBOLUCQU6VRCET2P","short_pith_number":"pith:5AXMADUI","canonical_record":{"source":{"id":"1804.01452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T15:03:08Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"d83abea2bdd412d4b70c714b789f597a7f865701cdb082b873c29962acc0dc03","abstract_canon_sha256":"a983ba976f77c904ab438a1ab2d4c1670b507e6fd8407e4bf8c37b19dba0856c"},"schema_version":"1.0"},"canonical_sha256":"e82ec00e88b856172e82853d588893d3c19a7f67b7923d7f53fa1e79c916cb81","source":{"kind":"arxiv","id":"1804.01452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01452","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01452v1","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01452","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"5AXMADUIXBLB","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5AXMADUIXBLBOLUC","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5AXMADUI","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5AXMADUIXBLBOLUCQU6VRCET2P","target":"record","payload":{"canonical_record":{"source":{"id":"1804.01452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T15:03:08Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"d83abea2bdd412d4b70c714b789f597a7f865701cdb082b873c29962acc0dc03","abstract_canon_sha256":"a983ba976f77c904ab438a1ab2d4c1670b507e6fd8407e4bf8c37b19dba0856c"},"schema_version":"1.0"},"canonical_sha256":"e82ec00e88b856172e82853d588893d3c19a7f67b7923d7f53fa1e79c916cb81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:15.013329Z","signature_b64":"hSY8aXyfSgylYu3Iy+9Z8lrrtZZq8y8IBrfPhlCALh2rGq45TpORu00I1S+r+H1o1KvP8tVV7act5lAkJnsFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e82ec00e88b856172e82853d588893d3c19a7f67b7923d7f53fa1e79c916cb81","last_reissued_at":"2026-05-18T00:19:15.012596Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:15.012596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.01452","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":"2026-05-18T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eNoRhqztaoU5aUEt0ULq7hGS9gPKFnfnCpVhniJzGuYny/q4fHu/TiMXDt6DHZh2bwiQyKqrp44OckH/UUGWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:27:46.939442Z"},"content_sha256":"ee1a9e079412fb085f0bdd627bac9e4134c9692ca417c485cfa089832241f676","schema_version":"1.0","event_id":"sha256:ee1a9e079412fb085f0bdd627bac9e4134c9692ca417c485cfa089832241f676"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5AXMADUIXBLBOLUCQU6VRCET2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.CV","authors_text":"Adri\\`a Recasens, Antonio Torralba, David Harwath, D\\'idac Sur\\'is, Galen Chuang, James Glass","submitted_at":"2018-04-04T15:03:08Z","abstract_excerpt":"In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01452","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":"2026-05-18T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPRWDZvsMx7SY3a0aLj7/yvSo+vhCScWL8UhMusKMlE+QogbPW8tgn6QoNow64tM3y/LubmnZ0aU5HV/PcrvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:27:46.940184Z"},"content_sha256":"c68849b4cd00accdda63986cab39e552b5c47ad669be375c07e5ac88cd4f5387","schema_version":"1.0","event_id":"sha256:c68849b4cd00accdda63986cab39e552b5c47ad669be375c07e5ac88cd4f5387"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5AXMADUIXBLBOLUCQU6VRCET2P/bundle.json","state_url":"https://pith.science/pith/5AXMADUIXBLBOLUCQU6VRCET2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5AXMADUIXBLBOLUCQU6VRCET2P/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":"2026-05-30T11:27:46Z","links":{"resolver":"https://pith.science/pith/5AXMADUIXBLBOLUCQU6VRCET2P","bundle":"https://pith.science/pith/5AXMADUIXBLBOLUCQU6VRCET2P/bundle.json","state":"https://pith.science/pith/5AXMADUIXBLBOLUCQU6VRCET2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5AXMADUIXBLBOLUCQU6VRCET2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5AXMADUIXBLBOLUCQU6VRCET2P","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":"a983ba976f77c904ab438a1ab2d4c1670b507e6fd8407e4bf8c37b19dba0856c","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T15:03:08Z","title_canon_sha256":"d83abea2bdd412d4b70c714b789f597a7f865701cdb082b873c29962acc0dc03"},"schema_version":"1.0","source":{"id":"1804.01452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01452","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01452v1","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01452","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"5AXMADUIXBLB","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5AXMADUIXBLBOLUC","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5AXMADUI","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:c68849b4cd00accdda63986cab39e552b5c47ad669be375c07e5ac88cd4f5387","target":"graph","created_at":"2026-05-18T00:19:15Z","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":"In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis","authors_text":"Adri\\`a Recasens, Antonio Torralba, David Harwath, D\\'idac Sur\\'is, Galen Chuang, James Glass","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T15:03:08Z","title":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01452","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:ee1a9e079412fb085f0bdd627bac9e4134c9692ca417c485cfa089832241f676","target":"record","created_at":"2026-05-18T00:19:15Z","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":"a983ba976f77c904ab438a1ab2d4c1670b507e6fd8407e4bf8c37b19dba0856c","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T15:03:08Z","title_canon_sha256":"d83abea2bdd412d4b70c714b789f597a7f865701cdb082b873c29962acc0dc03"},"schema_version":"1.0","source":{"id":"1804.01452","kind":"arxiv","version":1}},"canonical_sha256":"e82ec00e88b856172e82853d588893d3c19a7f67b7923d7f53fa1e79c916cb81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e82ec00e88b856172e82853d588893d3c19a7f67b7923d7f53fa1e79c916cb81","first_computed_at":"2026-05-18T00:19:15.012596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:15.012596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hSY8aXyfSgylYu3Iy+9Z8lrrtZZq8y8IBrfPhlCALh2rGq45TpORu00I1S+r+H1o1KvP8tVV7act5lAkJnsFAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:15.013329Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee1a9e079412fb085f0bdd627bac9e4134c9692ca417c485cfa089832241f676","sha256:c68849b4cd00accdda63986cab39e552b5c47ad669be375c07e5ac88cd4f5387"],"state_sha256":"59628c0d38b4f2908c1efe2e6823caca7912946640ba1cb8d7d29f83b33aaadf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1jT8yw9FZTIxWud6DD8+/ZU3GaGCVWBo7+Errp+HNy1C4QVyaqMr3GfHVJQVGyOoS8dm5u7dxhbjJrtqzzfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:27:46.944602Z","bundle_sha256":"c3f16ac39a597d7af16d1aefc53bd08dc872196ca1ff3ba014c83d9e4324058f"}}