{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CL5I4QGYAWKSTUGMJZC5SKHHMU","short_pith_number":"pith:CL5I4QGY","schema_version":"1.0","canonical_sha256":"12fa8e40d8059529d0cc4e45d928e76509ad59a9c03cad01587f394dd0e75c39","source":{"kind":"arxiv","id":"1907.12336","version":2},"attestation_state":"computed","paper":{"title":"Goal-Driven Sequential Data Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tao Xiang, Timothy M. Hospedales, Umar Riaz Muhammad, Yi-Zhe Song, Yongxin Yang","submitted_at":"2019-07-29T11:24:51Z","abstract_excerpt":"Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction. In the latter this capability is exploited for saving space or human time by summarizing the essence of input data. In this paper we study a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way. The ability to define different abstraction goals uniquely"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1907.12336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-29T11:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"8bd1900531692efe7abbb9f208a6d81f289e8c21b420934a7c9539ae4c537135","abstract_canon_sha256":"b09e4dc1d9e1142793e2e2c521ec9fdc9c5a1e14f571d8e656fb7e6df17c059f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:22.259270Z","signature_b64":"QVvpmGcmAvNGt4aXDMZhD6nev5JrU9VZ+TNz3uKjYVq9x5KZgo2ial4UavNRh2joBTolLopiggXkHk4mx/3pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12fa8e40d8059529d0cc4e45d928e76509ad59a9c03cad01587f394dd0e75c39","last_reissued_at":"2026-07-04T23:52:22.258882Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:22.258882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goal-Driven Sequential Data Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tao Xiang, Timothy M. Hospedales, Umar Riaz Muhammad, Yi-Zhe Song, Yongxin Yang","submitted_at":"2019-07-29T11:24:51Z","abstract_excerpt":"Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction. In the latter this capability is exploited for saving space or human time by summarizing the essence of input data. In this paper we study a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way. The ability to define different abstraction goals uniquely"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12336","kind":"arxiv","version":2},"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/1907.12336/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.12336","created_at":"2026-07-04T23:52:22.258947+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.12336v2","created_at":"2026-07-04T23:52:22.258947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12336","created_at":"2026-07-04T23:52:22.258947+00:00"},{"alias_kind":"pith_short_12","alias_value":"CL5I4QGYAWKS","created_at":"2026-07-04T23:52:22.258947+00:00"},{"alias_kind":"pith_short_16","alias_value":"CL5I4QGYAWKSTUGM","created_at":"2026-07-04T23:52:22.258947+00:00"},{"alias_kind":"pith_short_8","alias_value":"CL5I4QGY","created_at":"2026-07-04T23:52:22.258947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU","json":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU.json","graph_json":"https://pith.science/api/pith-number/CL5I4QGYAWKSTUGMJZC5SKHHMU/graph.json","events_json":"https://pith.science/api/pith-number/CL5I4QGYAWKSTUGMJZC5SKHHMU/events.json","paper":"https://pith.science/paper/CL5I4QGY"},"agent_actions":{"view_html":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU","download_json":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU.json","view_paper":"https://pith.science/paper/CL5I4QGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.12336&json=true","fetch_graph":"https://pith.science/api/pith-number/CL5I4QGYAWKSTUGMJZC5SKHHMU/graph.json","fetch_events":"https://pith.science/api/pith-number/CL5I4QGYAWKSTUGMJZC5SKHHMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU/action/storage_attestation","attest_author":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU/action/author_attestation","sign_citation":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU/action/citation_signature","submit_replication":"https://pith.science/pith/CL5I4QGYAWKSTUGMJZC5SKHHMU/action/replication_record"}},"created_at":"2026-07-04T23:52:22.258947+00:00","updated_at":"2026-07-04T23:52:22.258947+00:00"}