Citation extraction - find every citation before you check it
Philosophy
You can only verify what you first find. Grounding a citation checks whether it exists in the
source - but it runs on a list that someone has to assemble first. This skill is that front-end: it
walks the text and lists every authority, so none slips past verification. A missed citation is an
unverified one.
Extraction is mechanical (patterns + rules, not an LLM) on purpose - a model asked to find
citations might miss one or invent one. Local, jurisdiction-neutral, EU-aware.
Three steps (after eyecite)
- Extraction - recognise and capture every reference by the patterns below.
- Aggregation - resolve short references (ibid. / id. / supra / op. cit. / "the above-cited
judgment") to their antecedents by the pointer-aware rules below, so they count as one citation,
not several.
- Hand-off - pass the structured list to verification (grounding) and, for EU sources, to
eu-sparql-search for retrieval.
Citation patterns
Case law
- ECLI (EU):
ECLI:EU:C:2020:559 (Court of Justice), ECLI:EU:T:2019:... (General Court).
- ECLI (national):
ECLI:NL:HR:2021:..., ECLI:DE:BGH:..., ECLI:PL:SN:....
- Case names / numbers:
Party v Party; CJEU case numbers C-123/20, C-123/20 P (appeal),
joined cases C-123/20 and C-124/20; General Court T-456/19.
EU legislation
- CELEX:
32016R0679, 32019L0790 (sector + year + type + number).
- Named acts:
Regulation (EU) 2016/679, Directive 2019/790, Regulation (EC) No 1/2003.
- Official Journal:
OJ L 119, OJ C 326.
Provisions
Article 5(1)(a) GDPR, Art. 263 TFEU, section 12, § 3(2).
Aggregation - short references (antecedents)
Short reference forms carry different resolution rules - they cannot all be sent to the nearest
antecedent:
ibid. / id. / loc. cit. - the immediately preceding authority.supra / op. cit. - often carry a pointer that overrides proximity: an author, a title
fragment, or a note number ("Kranenborg, op. cit., p. 12"; "supra note 14"). Resolve by the pointer
first; fall back to proximity only when the reference is bare.- Descriptive forms (
the cited judgment, the above-cited) - match by described attributes (court,
party, subject), not position alone.
Where more than one antecedent matches, or none does, mark the reference unresolved - manual
review instead of guessing: a wrong merge silently fuses two distinct authorities into one. Count
each resolved reference as the same citation as its antecedent, but keep where it occurs.
Output format
CITATIONS FOUND (n):
| # | Type | Citation (normalised) | Occurrences (offset/page) | Antecedent (if short ref) |
| 1 | EU case law | C-311/18 (Schrems II) | p.3, p.7 (ibid.) | - |
| 2 | EU legislation | Regulation (EU) 2016/679 | p.2 | - |
| 3 | provision | Article 5(1)(a) GDPR | p.4 | - |
TO VERIFY: pass the "Citation" column to grounding; EU sources to eu-sparql-search.
Limits
- Extraction catches references in a known format. A descriptive reference with no identifier ("the
Court's data-protection case law") has nothing to match - mark it "no identifier, manual check".
- This is not existence verification - it says what is cited, not whether the citation is real.
- Patterns cover the common EU/ECLI formats; an unusual citation style may slip - at high stakes,
review by hand as well.
Attribution
The extraction -> aggregation -> annotation architecture is based on eyecite (Free Law Project),
BSD-2-Clause. US reporter regexes dropped; ECLI, CELEX/OJ and EU-citation patterns and the
antecedent rules are MateMatic's own. MateMatic interpretation, not the position of any bar or regulator.
1---2name: citation-extraction-en3description: Extracts the legal citations from an English-language text by pattern and rule, with no LLM in the extraction step, so the same text yields the same list every run - ECLI (CJEU and national), EU act identifiers (CELEX, Official Journal references, Regulation and Directive numbers), case names, and cited provisions (Article/section). It then normalises, deduplicates and resolves short references (ibid., id., supra, op. cit., the above-cited judgment) to their antecedent. The front end to verification: collect what is cited, then check it. Unusual or malformed citation formats can still be missed, so treat the output as a working list rather than a guarantee. Jurisdiction-neutral, EU-aware. Use when: "list every citation in this text", "what authorities are cited", "extract the provisions", "pull the case references", "what is cited here" - before verification or before sending.4license: Apache-2.05---67# Citation extraction - find every citation before you check it89## Philosophy1011**You can only verify what you first find.** Grounding a citation checks whether it exists in the12source - but it runs on a list that someone has to assemble first. This skill is that front-end: it13walks the text and lists every authority, so none slips past verification. A missed citation is an14unverified one.1516Extraction is **mechanical** (patterns + rules, not an LLM) on purpose - a model asked to find17citations might miss one or invent one. Local, jurisdiction-neutral, EU-aware.1819## Three steps (after eyecite)20211. **Extraction** - recognise and capture every reference by the patterns below.222. **Aggregation** - resolve short references (ibid. / id. / supra / op. cit. / "the above-cited23 judgment") to their antecedents by the pointer-aware rules below, so they count as one citation,24 not several.253. **Hand-off** - pass the structured list to verification (grounding) and, for EU sources, to26 eu-sparql-search for retrieval.2728## Citation patterns2930### Case law31- **ECLI (EU)**: `ECLI:EU:C:2020:559` (Court of Justice), `ECLI:EU:T:2019:...` (General Court).32- **ECLI (national)**: `ECLI:NL:HR:2021:...`, `ECLI:DE:BGH:...`, `ECLI:PL:SN:...`.33- **Case names / numbers**: `Party v Party`; CJEU case numbers `C-123/20`, `C-123/20 P` (appeal),34 joined cases `C-123/20 and C-124/20`; General Court `T-456/19`.3536### EU legislation37- **CELEX**: `32016R0679`, `32019L0790` (sector + year + type + number).38- **Named acts**: `Regulation (EU) 2016/679`, `Directive 2019/790`, `Regulation (EC) No 1/2003`.39- **Official Journal**: `OJ L 119`, `OJ C 326`.4041### Provisions42- `Article 5(1)(a) GDPR`, `Art. 263 TFEU`, `section 12`, `§ 3(2)`.4344## Aggregation - short references (antecedents)4546Short reference forms carry **different resolution rules** - they cannot all be sent to the nearest47antecedent:4849- `ibid.` / `id.` / `loc. cit.` - the immediately preceding authority.50- `supra` / `op. cit.` - often carry a **pointer** that overrides proximity: an author, a title51 fragment, or a note number ("Kranenborg, op. cit., p. 12"; "supra note 14"). Resolve by the pointer52 first; fall back to proximity only when the reference is bare.53- Descriptive forms (`the cited judgment`, `the above-cited`) - match by described attributes (court,54 party, subject), not position alone.5556Where more than one antecedent matches, or none does, mark the reference **unresolved - manual57review** instead of guessing: a wrong merge silently fuses two distinct authorities into one. Count58each resolved reference as the same citation as its antecedent, but keep where it occurs.5960## Output format6162```63CITATIONS FOUND (n):64| # | Type | Citation (normalised) | Occurrences (offset/page) | Antecedent (if short ref) |65| 1 | EU case law | C-311/18 (Schrems II) | p.3, p.7 (ibid.) | - |66| 2 | EU legislation | Regulation (EU) 2016/679 | p.2 | - |67| 3 | provision | Article 5(1)(a) GDPR | p.4 | - |6869TO VERIFY: pass the "Citation" column to grounding; EU sources to eu-sparql-search.70```7172## Limits7374- Extraction catches references in a known format. A descriptive reference with no identifier ("the75 Court's data-protection case law") has nothing to match - mark it "no identifier, manual check".76- This is not existence verification - it says what is cited, not whether the citation is real.77- Patterns cover the common EU/ECLI formats; an unusual citation style may slip - at high stakes,78 review by hand as well.7980## Attribution8182The extraction -> aggregation -> annotation architecture is based on **eyecite** (Free Law Project),83**BSD-2-Clause**. US reporter regexes dropped; ECLI, CELEX/OJ and EU-citation patterns and the84antecedent rules are MateMatic's own. MateMatic interpretation, not the position of any bar or regulator.
matematicsolutions