{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:D73KBINUSKM5RIKBZAUFXYWECU","short_pith_number":"pith:D73KBINU","canonical_record":{"source":{"id":"1701.07481","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-25T20:40:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4bbb8d533a22456497d6c6ef9f7d9aa499725439c9aacc7d8c161cee86505728","abstract_canon_sha256":"29e60aa20ed8c9d45c5215f419e7e6383d19acc40ca8401b26d00752bd486743"},"schema_version":"1.0"},"canonical_sha256":"1ff6a0a1b49299d8a141c8285be2c4151842e7ea4023123b2c60fdf2fc8fe593","source":{"kind":"arxiv","id":"1701.07481","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.07481","created_at":"2026-05-18T00:43:43Z"},{"alias_kind":"arxiv_version","alias_value":"1701.07481v3","created_at":"2026-05-18T00:43:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.07481","created_at":"2026-05-18T00:43:43Z"},{"alias_kind":"pith_short_12","alias_value":"D73KBINUSKM5","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"D73KBINUSKM5RIKB","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"D73KBINU","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:D73KBINUSKM5RIKBZAUFXYWECU","target":"record","payload":{"canonical_record":{"source":{"id":"1701.07481","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-25T20:40:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4bbb8d533a22456497d6c6ef9f7d9aa499725439c9aacc7d8c161cee86505728","abstract_canon_sha256":"29e60aa20ed8c9d45c5215f419e7e6383d19acc40ca8401b26d00752bd486743"},"schema_version":"1.0"},"canonical_sha256":"1ff6a0a1b49299d8a141c8285be2c4151842e7ea4023123b2c60fdf2fc8fe593","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:43.266640Z","signature_b64":"8a3iX/q/Sy0D3xqnZEkhvJGtcIuMZeikDTf69ft2le6SSgIhtW8Gf61Xc6/MY4fG7CnOVpNVOfwq/YXWO52eDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ff6a0a1b49299d8a141c8285be2c4151842e7ea4023123b2c60fdf2fc8fe593","last_reissued_at":"2026-05-18T00:43:43.266168Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:43.266168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.07481","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/8T5AKJ9W1blOkOSYprv9y8VVifypZUtIapvidQ0kAg6fQjoLny36NMd41KsJmtnlQc3aUFjzwC4MmeWlZPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:06:20.565085Z"},"content_sha256":"22c92ffe4d9f111a33e4fa59bd8b103fd5fb21f29c4523ab90bcd4b26a4e2f69","schema_version":"1.0","event_id":"sha256:22c92ffe4d9f111a33e4fa59bd8b103fd5fb21f29c4523ab90bcd4b26a4e2f69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:D73KBINUSKM5RIKBZAUFXYWECU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Word-Like Units from Joint Audio-Visual Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"David Harwath, James R. Glass","submitted_at":"2017-01-25T20:40:56Z","abstract_excerpt":"Given a collection of images and spoken audio captions, we present a method for discovering word-like acoustic units in the continuous speech signal and grounding them to semantically relevant image regions. For example, our model is able to detect spoken instances of the word 'lighthouse' within an utterance and associate them with image regions containing lighthouses. We do not use any form of conventional automatic speech recognition, nor do we use any text transcriptions or conventional linguistic annotations. Our model effectively implements a form of spoken language acquisition, in which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.07481","kind":"arxiv","version":3},"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":"2026-05-18T00:43:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pV8/+37ff2EYMBRACdZW4hUfd5+Edo8ZnR6rt17Km1l4+P+LsMyIZ8AsHICvibFoOSFpZrcQSA5w8iBxFaR9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:06:20.565796Z"},"content_sha256":"9650e3a0402acd0d9178b6d713cbccdd9eafd396cba8da7e7f16d1acbc752a7f","schema_version":"1.0","event_id":"sha256:9650e3a0402acd0d9178b6d713cbccdd9eafd396cba8da7e7f16d1acbc752a7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D73KBINUSKM5RIKBZAUFXYWECU/bundle.json","state_url":"https://pith.science/pith/D73KBINUSKM5RIKBZAUFXYWECU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D73KBINUSKM5RIKBZAUFXYWECU/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":"2026-05-30T12:06:20Z","links":{"resolver":"https://pith.science/pith/D73KBINUSKM5RIKBZAUFXYWECU","bundle":"https://pith.science/pith/D73KBINUSKM5RIKBZAUFXYWECU/bundle.json","state":"https://pith.science/pith/D73KBINUSKM5RIKBZAUFXYWECU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D73KBINUSKM5RIKBZAUFXYWECU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:D73KBINUSKM5RIKBZAUFXYWECU","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":"29e60aa20ed8c9d45c5215f419e7e6383d19acc40ca8401b26d00752bd486743","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-25T20:40:56Z","title_canon_sha256":"4bbb8d533a22456497d6c6ef9f7d9aa499725439c9aacc7d8c161cee86505728"},"schema_version":"1.0","source":{"id":"1701.07481","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.07481","created_at":"2026-05-18T00:43:43Z"},{"alias_kind":"arxiv_version","alias_value":"1701.07481v3","created_at":"2026-05-18T00:43:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.07481","created_at":"2026-05-18T00:43:43Z"},{"alias_kind":"pith_short_12","alias_value":"D73KBINUSKM5","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"D73KBINUSKM5RIKB","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"D73KBINU","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:9650e3a0402acd0d9178b6d713cbccdd9eafd396cba8da7e7f16d1acbc752a7f","target":"graph","created_at":"2026-05-18T00:43:43Z","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":"Given a collection of images and spoken audio captions, we present a method for discovering word-like acoustic units in the continuous speech signal and grounding them to semantically relevant image regions. For example, our model is able to detect spoken instances of the word 'lighthouse' within an utterance and associate them with image regions containing lighthouses. We do not use any form of conventional automatic speech recognition, nor do we use any text transcriptions or conventional linguistic annotations. Our model effectively implements a form of spoken language acquisition, in which","authors_text":"David Harwath, James R. Glass","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-25T20:40:56Z","title":"Learning Word-Like Units from Joint Audio-Visual Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.07481","kind":"arxiv","version":3},"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":"sha256:22c92ffe4d9f111a33e4fa59bd8b103fd5fb21f29c4523ab90bcd4b26a4e2f69","target":"record","created_at":"2026-05-18T00:43:43Z","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":"29e60aa20ed8c9d45c5215f419e7e6383d19acc40ca8401b26d00752bd486743","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-25T20:40:56Z","title_canon_sha256":"4bbb8d533a22456497d6c6ef9f7d9aa499725439c9aacc7d8c161cee86505728"},"schema_version":"1.0","source":{"id":"1701.07481","kind":"arxiv","version":3}},"canonical_sha256":"1ff6a0a1b49299d8a141c8285be2c4151842e7ea4023123b2c60fdf2fc8fe593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ff6a0a1b49299d8a141c8285be2c4151842e7ea4023123b2c60fdf2fc8fe593","first_computed_at":"2026-05-18T00:43:43.266168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:43.266168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8a3iX/q/Sy0D3xqnZEkhvJGtcIuMZeikDTf69ft2le6SSgIhtW8Gf61Xc6/MY4fG7CnOVpNVOfwq/YXWO52eDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:43.266640Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.07481","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22c92ffe4d9f111a33e4fa59bd8b103fd5fb21f29c4523ab90bcd4b26a4e2f69","sha256:9650e3a0402acd0d9178b6d713cbccdd9eafd396cba8da7e7f16d1acbc752a7f"],"state_sha256":"c67e9dd20a12b5fa77b6020a0c700801802e00be6174fb584498a947c164300e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CasbQz/3nGAW2kPhzPbhY0zSRsVwjR3xdSvzZiwAo6axC+6We2avS6tOxB4eMpQrILUpTDIfuM0R3W5n45GICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:06:20.569308Z","bundle_sha256":"b01c83492b21c01f7d1f0a2e27cebb0981f03e66e81827593e5056dab4a3585c"}}